Awesome-NeurIPS2019-NIPS

人工智能和机器学习领域的国际顶级会议NeurIPS论文收集

人工智能和机器学习领域的国际顶级会议NeurIPS 2019公布了接受论文，有效提交论文6743篇论文，总共有1428接受论文, 21.1%接受率，包括36篇Oral，164篇Spotlights。

本内容现在是NIPS2019,后期会随时更新为

Awesome-NIPS2019 陆续更新录用论文

论文下载百度云链接：链接：https://pan.baidu.com/s/100OAXTIOTPoMjbi-dwOcxA

提取码：请关注【计算机视觉联盟】微信公众号，回复：NIPS2019

Last updated: 2019/09/19

Update log

2019/09/04 * - 更新
2019/09/06 * - 更新1428篇所有文章

NeurIPS是人工智能和机器学习领域的国际顶级会议，由NIPS基金会负责运营。该会议全称为神经信息处理系统大会(Conference and Workshop on Neural Information Processing Systems，NIPS)，自1987年开始，每年的12月份，来自世界各地的从事AI和ML相关的专家学者和从业人士汇聚一堂。受其名称歧义带来的压力（部分原因是其首字母缩写具有「暧昧的内涵」，带有性别歧视的意义），2018年的会议名称改为NeurIPS 。

NeurIPS 2019将在12月8号加拿大温哥华会议中心举行。 https://neurips.cc/Conferences/2019/AcceptedPapersInitial

NeurIPS 2019接受论文推荐

理解图神经网络的表示能力，

Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology

https://arxiv.org/abs/1907.05008

Visualizing the PHATE of Neural Networks，

https://arxiv.org/abs/1908.02831

多模态元学习，Toward Multimodal Model-Agnostic Meta-Learning

https://arxiv.org/pdf/1812.07172.pdf

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation

https://arxiv.org/abs/1905.11722

RUBi: Reducing Unimodal Biases in Visual Question Answering

http://arxiv.org/abs/1906.10169

Code: http://github.com/cdancette/rubi.bootstrap.pytorch

理解图神经网络中的注意力与泛化机制，Understanding Attention and Generalization in Graph Neural Networks

https://arxiv.org/pdf/1905.02850.pdf

Facebook提出跨语言预训练模型XLM，Cross-lingual Language Model Pretraining

https://arxiv.org/pdf/1901.07291.pdf

超图卷积神经网络， HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs

https://arxiv.org/abs/1809.02589

四元知识图谱嵌入，Quaternion Knowledge Graph Embeddings

https://arxiv.org/pdf/1904.10281.pdf

理解医学图像中的迁移学习，Transfusion: Understanding Transfer Learning for Medical Imaging

https://arxiv.org/pdf/1902.07208.pdf

全部

Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation

Risto Vuorio (University of Michigan) • Shao-Hua Sun (University of Southern California) • Hexiang Hu (University of Southern California) • Joseph J Lim (University of Southern California)

ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

Jiasen Lu (Georgia Tech) • Dhruv Batra (Georgia Tech / Facebook AI Research (FAIR)) • Devi Parikh (Georgia Tech / Facebook AI Research (FAIR)) • Stefan Lee (Georgia Institute of Technology)

Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers

Liwei Wu (University of California, Davis) • Shuqing Li (University of California, Davis) • Cho-Jui Hsieh (UCLA) • James Sharpnack (UC Davis)

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

JiaWang Bian (The University of Adelaide) • Zhichao Li (Tusimple) • Naiyan Wang (Hong Kong University of Science and Technology) • Huangying Zhan (The University of Adelaide) • Chunhua Shen (University of Adelaide) • Ming-Ming Cheng (Nankai University) • Ian Reid (University of Adelaide)

Zero-shot Learning via Simultaneous Generating and Learning

Hyeonwoo Yu (Seoul National University) • Beomhee Lee (Seoul National University)

Ask not what AI can do for you, but what AI should do: Towards a framework of task delegability

Brian Lubars (University of Colorado Boulder) • Chenhao Tan (University of Colorado Boulder)

Stand-Alone Self-Attention in Vision Models

Niki Parmar (Google) • Prajit Ramachandran (Google Brain) • Ashish Vaswani (Google Brain) • Irwan Bello (Google) • Anselm Levskaya (Google) • Jon Shlens (Google Research)

High Fidelity Video Prediction with Large Neural Nets

Ruben Villegas (Adobe Research / U. Michigan) • Arkanath Pathak (Google) • Harini Kannan (Google Brain) • Honglak Lee (Google / U. Michigan) • Dumitru Erhan (Google Brain) • Quoc V Le (Google)

Unsupervised learning of object structure and dynamics from videos

Matthias Minderer (Google Research) • Chen Sun (Google Research) • Ruben Villegas (Adobe Research / U. Michigan) • Forrester Cole (Google Research) • Kevin P Murphy (Google) • Honglak Lee (Google Brain)

TensorPipe: Easy Scaling with Micro-Batch Pipeline Parallelism

Yanping Huang (Google Brain) • Youlong Cheng (Google) • Ankur Bapna (Google) • Orhan Firat (Google) • Dehao Chen (Google) • Mia Chen (Google Brain) • HyoukJoong Lee (Google) • Jiquan Ngiam (Google Brain) • Quoc V Le (Google) • Yonghui Wu (Google) • zhifeng Chen (Google Brain)

Meta-Learning with Implicit Gradients

Aravind Rajeswaran (University of Washington) • Chelsea Finn (Stanford University) • Sham Kakade (University of Washington) • Sergey Levine (UC Berkeley)

Adversarial Examples Are Not Bugs, They Are Features

Andrew Ilyas (MIT) • Shibani Santurkar (MIT) • Dimitris Tsipras (MIT) • Logan Engstrom (MIT) • Brandon Tran (Massachusetts Institute of Technology) • Aleksander Madry (MIT)

Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks

Vineet Kosaraju (Stanford University) • Amir Sadeghian (Stanford University) • Roberto Martín-Martín (Stanford University) • Ian Reid (University of Adelaide) • Hamid Rezatofighi (University of Adelaide) • Silvio Savarese (Stanford University)

FreeAnchor: Learning to Match Anchors for Visual Object Detection

Xiaosong Zhang (University of Chinese Academy of Sciences) • Fang Wan (University of Chinese Academy of Sciences) • Chang Liu (University of Chinese Academy of Sciences) • Rongrong Ji (Xiamen University, China) • Qixiang Ye (University of Chinese Academy of Sciences, China)

Differentially Private Hypothesis Selection

Mark Bun (Princeton University) • Gautam Kamath (University of Waterloo) • Thomas Steinke (IBM, Almaden) • Steven Wu (Microsoft Research)

New Differentially Private Algorithms for Learning Mixtures of Well-Separated Gaussians

Gautam Kamath (University of Waterloo) • Or Sheffet (University of Alberta) • Vikrant Singhal (Northeastern University) • Jonathan Ullman (Northeastern University)

Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation

Mark Bun (Princeton University) • Thomas Steinke (IBM, Almaden)

Multi-Resolution Weak Supervision for Sequential Data

Paroma Varma (Stanford University) • Frederic Sala (Stanford) • Shiori Sagawa (Stanford University) • Jason Fries (Stanford University) • Daniel Fu (Stanford University) • Saelig Khattar (Stanford University) • Ashwini Ramamoorthy (Stanford University) • Ke Xiao (Stanford University) • Kayvon Fatahalian (Stanford) • James Priest (Stanford University) • Christopher Ré (Stanford)

DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision

Tam Nguyen (Freiburg Computer Vision Lab) • Maximilian Dax (Bosch GmbH) • Chaithanya Kumar Mummadi (Robert Bosch GmbH) • Nhung Ngo (Bosch Center for Artificial Intelligence) • Thi Hoai Phuong Nguyen (KIT) • Zhongyu Lou (Robert Bosch Gmbh) • Thomas Brox (University of Freiburg)

The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection

Vladimir V. Kniaz (IEEE) • Vladimir Knyaz (State Research Institute of Aviation Systems) • Fabio Remondino ("Fondazione Bruno Kessler, Italy")

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle

Dinghuai Zhang (Peking University) • Tianyuan Zhang (Peking University) • Yiping Lu (Peking University) • Zhanxing Zhu (Peking University) • Bin Dong (Peking University)

Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement

Chao Yang (Tsinghua University) • Xiaojian Ma (University of California, Los Angeles) • Wenbing Huang (Tsinghua University) • Fuchun Sun (Tsinghua) • 刘华平 (清华大学) • Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) • Chuang Gan (MIT-IBM Watson AI Lab)

Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance

Kimia Nadjahi ( Télécom ParisTech) • Alain Durmus (ENS) • Umut Simsekli (Institut Polytechnique de Paris) • Roland Badeau (Télécom ParisTech)

Generalized Sliced Wasserstein Distances

Soheil Kolouri (HRL Laboratories LLC) • Kimia Nadjahi ( Télécom ParisTech) • Umut Simsekli (Institut Polytechnique de Paris) • Roland Badeau (Télécom ParisTech) • Gustavo Rohde (University of Virginia)

First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise

Than Huy Nguyen (Telecom ParisTech) • Umut Simsekli (Institut Polytechnique de Paris) • Mert Gurbuzbalaban (Rutgers) • Gaël RICHARD (Télécom ParisTech)

Blind Super-Resolution Kernel Estimation using an Internal-GAN

Yosef Bell Kligler (Weizmann Istitute of Science) • Assaf Shocher (Weizmann Institute of Science) • Michal Irani (The Weizmann Institute of Science)

Noise-tolerant fair classification

Alex Lamy (Columbia University) • Ziyuan Zhong (Columbia University) • Aditya Menon (Google) • Nakul Verma (Columbia University)

Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection

Bingzhe Wu (Peeking University) • Shiwan Zhao (IBM Research - China) • Haoyang Xu (Peking University) • Chaochao Chen (Ant Financial) • Li Wang (Ant Financial) • Xiaolu Zhang (Ant Financial Services Group) • Guangyu Sun (Peking University) • Jun Zhou (Ant Financial)

Joint-task Self-supervised Learning for Temporal Correspondence

xueting li (uc merced) • Sifei Liu (NVIDIA) • Shalini De Mello (NVIDIA) • Xiaolong Wang (CMU) • Jan Kautz (NVIDIA) • Ming-Hsuan Yang (UC Merced / Google)

Provable Gradient Variance Guarantees for Black-Box Variational Inference

Justin Domke (University of Massachusetts, Amherst)

Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation

Justin Domke (University of Massachusetts, Amherst) • Daniel Sheldon (University of Massachusetts Amherst)

Experience Replay for Continual Learning

David Rolnick (UPenn) • Arun Ahuja (DeepMind) • Jonathan Schwarz (DeepMind) • Timothy Lillicrap (Google DeepMind) • Gregory Wayne (Google DeepMind)

Deep ReLU Networks Have Surprisingly Few Activation Patterns

Boris Hanin (Texas A&M) • David Rolnick (UPenn)

Chasing Ghosts: Instruction Following as Bayesian State Tracking

Peter Anderson (Georgia Tech) • Ayush Shrivastava (Georgia Institute of Technology) • Devi Parikh (Georgia Tech / Facebook AI Research (FAIR)) • Dhruv Batra (Georgia Tech / Facebook AI Research (FAIR)) • Stefan Lee (Georgia Institute of Technology)

Block Coordinate Regularization by Denoising

Yu Sun (Washington University in St. Louis) • Jiaming Liu (Washington University in St. Louis) • Ulugbek Kamilov (Washington University in St. Louis)

Reducing Noise in GAN Training with Variance Reduced Extragradient

Tatjana Chavdarova (Mila & Idiap & EPFL) • Gauthier Gidel (Mila) • François Fleuret (Idiap Research Institute) • Simon Lacoste-Julien (Mila, Université de Montréal)

Learning Erdos-Renyi Random Graphs via Edge Detecting Queries

Zihan Li (National University of Singapore) • Matthias Fresacher (University of Adelaide) • Jonathan Scarlett (National University of Singapore)

A Primal-Dual link between GANs and Autoencoders

Hisham Husain (The Australian National University) • Richard Nock (Data61, the Australian National University and the University of Sydney) • Robert Williamson (Australian National University & Data61)

muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking

CONGCHAO WANG (Virginia Tech) • Yizhi Wang (Virginia Tech) • Yinxue Wang (Virginia Tech) • Chiung-Ting Wu (Virginia Tech) • Guoqiang Yu (Virginia Tech)

Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

Qiming Zhang (the University of Sydney) • Jing Zhang (The University of Sydney) • Wei Liu (Tencent AI Lab) • Dacheng Tao (University of Sydney)

Invert to Learn to Invert

Patrick Putzky (University of Amsterdam) • Max Welling (University of Amsterdam / Qualcomm AI Research)

Equitable Stable Matchings in Quadratic Time

Nikolaos Tziavelis (Northeastern University) • Ioannis Giannakopoulos (National Technical University of Athens) • Katerina Doka (NTUA) • Nectarios Koziris (NTUA) • Panagiotis Karras (Aarhus University)

Zero-Shot Semantic Segmentation

Maxime Bucher (Valeo.ai) • Tuan-Hung VU (Valeo.ai) • Matthieu Cord (Sorbonne University) • Patrick Pérez (Valeo.ai)

Metric Learning for Adversarial Robustness

Chengzhi Mao (Columbia University) • Ziyuan Zhong (Columbia University) • Junfeng Yang (Columbia University) • Carl Vondrick (Columbia University) • Baishakhi Ray (Columbia University)

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

Qiangeng Xu (USC) • Weiyue Wang (USC) • Duygu Ceylan (Adobe Research) • Radomir Mech (Adobe Systems Incorporated) • Ulrich Neumann (USC)

Batched Multi-armed Bandits Problem

Zijun Gao (Stanford University) • Yanjun Han (Stanford University) • Zhimei Ren (Stanford University) • Zhengqing Zhou (Stanford University)

vGraph: A Generative Model for Joint Community Detection and Node Representation Learning

Fan-Yun Sun (National Taiwan University) • Meng Qu (MILA) • Jordan Hoffmann (Harvard University/Mila) • Chin-Wei Huang (MILA) • Jian Tang (HEC Montreal & MILA)

Differentially Private Bayesian Linear Regression

Garrett Bernstein (University of Massachusetts Amherst) • Daniel Sheldon (University of Massachusetts Amherst)

Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos

Yitian Yuan (Tsinghua University) • Lin Ma (Tencent AI Lab) • Jingwen Wang (Tencent AI Lab) • Wei Liu (Tencent AI Lab) • Wenwu Zhu (Tsinghua University)

AGEM: Solving Linear Inverse Problems via Deep Priors and Sampling

Bichuan Guo (Tsinghua University) • Yuxing Han (South China Agriculture University) • Jiangtao Wen (Tsinghua University)

CPM-Nets: Cross Partial Multi-View Networks

Changqing Zhang (Tianjin university) • Zongbo Han (Tianjin University) • yajie cui (tianjin university) • Huazhu Fu (Inception Institute of Artificial Intelligence) • Joey Tianyi Zhou (IHPC, A*STAR) • Qinghua Hu (Tianjin University)

Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis

Xihui Liu (The Chinese University of Hong Kong) • Guojun Yin (University of Science and Technology of China) • Jing Shao (Sensetime) • Xiaogang Wang (The Chinese University of Hong Kong) • hongsheng Li (cuhk)

Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling

Andrey Kolobov (Microsoft Research) • Yuval Peres (N/A) • Cheng Lu (Microsoft) • Eric J Horvitz (Microsoft Research)

SySCD: A System-Aware Parallel Coordinate Descent Algorithm

Celestine Mendler-Dünner (UC Berkeley) • Nikolas Ioannou (IBM Research) • Thomas Parnell (IBM Research)

Importance Weighted Hierarchical Variational Inference

Artem Sobolev (Samsung) • Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow)

RSN: Randomized Subspace Newton

Robert Gower (Telecom-Paristech) • Dmitry Koralev (KAUST) • Felix Lieder (Heinrich-Heine-Universität Düsseldorf) • Peter Richtarik (KAUST)

Trust Region-Guided Proximal Policy Optimization

Yuhui Wang (Nanjing University of Aeronautics and Astronautics, China) • Hao He (Nanjing University of Aeronautics and Astronautics) • Xiaoyang Tan (Nanjing University of Aeronautics and Astronautics, China) • Yaozhong Gan (Nanjing University of Aeronautics and Astronautics, China)

Adversarial Self-Defense for Cycle-Consistent GANs

Dina Bashkirova (Boston University) • Ben Usman (Boston University) • Kate Saenko (Boston University)

Towards closing the gap between the theory and practice of SVRG

Othmane Sebbouh (Télécom ParisTech) • Nidham Gazagnadou (Télécom ParisTech) • Samy Jelassi (Princeton University) • Francis Bach (INRIA - Ecole Normale Superieure) • Robert Gower (Telecom-Paristech)

Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control

Armin Lederer (Technical University of Munich) • Jonas Umlauft (Technical University of Munich) • Sandra Hirche (Technische Universitaet Muenchen)

ETNet: Error Transition Network for Arbitrary Style Transfer

Chunjin Song (Shenzhen University) • Zhijie Wu (Shenzhen University) • Yang Zhou (Shenzhen University) • Minglun Gong (Memorial Univ) • Hui Huang (Shenzhen University)

No Pressure! Addressing the Problem of Local Minima in Manifold Learning Algorithms

Max Vladymyrov (Google)

Deep Equilibrium Models

Shaojie Bai (Carnegie Mellon University) • J. Zico Kolter (Carnegie Mellon University / Bosch Center for AI) • Vladlen Koltun (Intel Labs)

Saccader: Accurate, Interpretable Image Classification with Hard Attention

Gamaleldin Elsayed (Google Brain) • Simon Kornblith (Google Brain) • Quoc V Le (Google)

Multiway clustering via tensor block models

Miaoyan Wang (University of Wisconsin - Madison) • Yuchen Zeng (University of Wisconsin - Madison)

Regret Minimization for Reinforcement Learning on Multi-Objective Online Markov Decision Processes

Wang Chi Cheung (Department of Industrial Systems Engineering and Management, National University of Singapore)

NAT: Neural Architecture Transformer for Accurate and Compact Architectures

Yong Guo (South China University of Technology) • Yin Zheng (Tencent AI Lab) • Mingkui Tan (South China University of Technology) • Qi Chen (South China University of Technology) • Jian Chen ("South China University of Technology, China") • Peilin Zhao (Tencent AI Lab) • Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)

Selecting Optimal Decisions via Distributionally Robust Nearest-Neighbor Regression

Ruidi Chen (Boston University) • Ioannis Paschalidis (Boston University)

Network Pruning via Transformable Architecture Search

Xuanyi Dong (University of Technology Sydney) • Yi Yang (UTS)

Differentiable Cloth Simulation for Inverse Problems

Junbang Liang (University of Maryland, College Park) • Ming Lin (UMD-CP & UNC-CH ) • Vladlen Koltun (Intel Labs)

Poisson-randomized Gamma Dynamical Systems

Aaron Schein (UMass Amherst) • Scott Linderman (Columbia University) • Mingyuan Zhou (University of Texas at Austin) • David Blei (Columbia University) • Hanna Wallach (MSR NYC)

Volumetric Correspondence Networks for Optical Flow

Gengshan Yang (Carnegie Mellon University) • Deva Ramanan (Carnegie Mellon University)

Learning Conditional Deformable Templates with Convolutional Networks

Adrian Dalca (MIT, HMS) • Marianne Rakic (ETH Zürich) • John Guttag (Massachusetts Institute of Technology) • Mert Sabuncu (Cornell)

Fast Low-rank Metric Learning for Large-scale and High-dimensional Data

Han Liu (Tsinghua University) • Zhizhong Han (University of Maryland, College Park) • Yu-Shen Liu (Tsinghua University) • Ming Gu (Tsinghua University)

Efficient Symmetric Norm Regression via Linear Sketching

Zhao Song (University of Washington) • Ruosong Wang (Carnegie Mellon University) • Lin Yang (Johns Hopkins University) • Hongyang Zhang (Carnegie Mellon University) • Peilin Zhong (Columbia University)

RUBi: Reducing Unimodal Biases in Visual Question Answering

Remi Cadene (LIP6) • Corentin Dancette (LIP6) • Hedi Ben younes (Université Pierre & Marie Curie / Heuritech) • Matthieu Cord (Sorbonne University) • Devi Parikh (Georgia Tech / Facebook AI Research (FAIR))

Reducing Scene Bias of Convolutional Neural Networks for Human Action Understanding

Jinwoo Choi (Virginia Tech) • Chen Gao (Virginia Tech) • Joseph C.E. Messou (Virginia Tech) • Jia-Bin Huang (Virginia Tech)

NeurVPS: Neural Vanishing Point Scanning via Conic Convolution

Yichao Zhou (UC Berkeley) • Haozhi Qi (UC Berkeley) • Jingwei Huang (Stanford University) • Yi Ma (UC Berkeley)

DATA: Differentiable ArchiTecture Approximation

Jianlong Chang (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences) • xinbang zhang (Institute of Automation,Chinese Academy of Science) • Yiwen Guo (Intel Labs China) • GAOFENG MENG (Institute of Automation, Chinese Academy of Sciences) • SHIMING XIANG (Chinese Academy of Sciences, China) • Chunhong Pan (Institute of Automation, Chinese Academy of Sciences)

Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge

Tingting Qiao (Zhejiang University) • Jing Zhang (The University of Sydney) • Duanqing Xu (Zhejiang University) • Dacheng Tao (University of Sydney)

Memory-oriented Decoder for Light Field Salient Object Detection

Miao Zhang (Dalian University of Technology) • Jingjing Li (Dalian University of Technology) • Wei Ji (Dalian University of Technology) • Yongri Piao (Dalian University of Technology) • Huchuan Lu (Dalian University of Technology)

Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition

Xuesong Niu (Institute of Computing Technology, CAS) • Hu Han (ICT, CAS) • Shiguang Shan (Chinese Academy of Sciences) • Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)

Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels

Natalia Neverova (Facebook AI Research) • David Novotny (Facebook AI Research) • Andrea Vedaldi (University of Oxford / Facebook AI Research)

Powerset Convolutional Neural Networks

Chris Wendler (ETH Zurich) • Markus Püschel (ETH Zurich) • Dan Alistarh (IST Austria)

Optimal Pricing in Repeated Posted-Price Auctions with Different Patience of the Seller and the Buyer

Arsenii Vanunts (Yandex) • Alexey Drutsa (Yandex)

An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums

Hadrien Hendrikx (INRIA) • Francis Bach (INRIA - Ecole Normale Superieure) • Laurent Massoulié (Inria)

Efficient 3D Deep Learning via Point-Based Representation and Voxel-Based Convolution

Zhijian Liu (MIT) • Haotian Tang (Shanghai Jiao Tong University) • Yujun Lin (MIT) • Song Han (MIT)

Deep Learning without Weight Transport

Mohamed Akrout (University of Toronto) • Collin Wilson (University of Toronto) • Peter Humphreys (Google) • Timothy Lillicrap (Google DeepMind) • Douglas Tweed (University of Toronto)

Combinatorial Bandits with Relative Feedback

Aadirupa Saha (Indian Institute of SCience) • Aditya Gopalan (Indian Institute of Science)

General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme

Tao Sun (National university of defense technology) • Yuejiao Sun (University of California, Los Angeles) • Dongsheng Li (School of Computer Science, National University of Defense Technology) • Qing Liao (Harbin Institute of Technology (Shenzhen))

Joint Optimizing of Cycle-Consistent Networks

Leonidas J Guibas (stanford.edu) • Qixing Huang (The University of Texas at Austin) • Zhenxiao Liang (The University of Texas at Austin)

Explicit Disentanglement of Appearance and Perspective in Generative Models

Nicki Skafte Detlefsen (Technical University of Denmark) • Søren Hauberg (Technical University of Denmark)

Polynomial Cost of Adaptation for X-Armed Bandits

Hedi Hadiji (Laboratoire de Mathematiques d’Orsay, Univ. Paris-Sud,)

Learning to Propagate for Graph Meta-Learning

LU LIU (University of Technology Sydney) • Tianyi Zhou (University of Washington, Seattle) • Guodong Long (University of Technology Sydney) • Jing Jiang (University of Technology Sydney) • Chengqi Zhang (University of Technology Sydney)

Secretary Ranking with Minimal Inversions

Sepehr Assadi (Princeton University) • Eric Balkanski (Harvard University) • Renato Leme (Google Research)

Nonparametric Regressive Point Processes Based on Conditional Gaussian Processes

Siqi Liu (University of Pittsburgh) • Milos Hauskrecht (University of Pittsburgh)

Learning Perceptual Inference by Contrasting

Chi Zhang (University of California, Los Angeles) • Baoxiong Jia (UCLA) • Feng Gao (UCLA) • Yixin Zhu (University of California, Los Angeles) • HongJing Lu (UCLA) • Song-Chun Zhu (UCLA)

Selecting the independent coordinates of manifolds with large aspect ratios

Yu-Chia Chen (University of Washington) • Marina Meila (University of Washington)

Region-specific Diffeomorphic Metric Mapping

Zhengyang Shen (University of North Carolina at Chapel Hill) • Francois-Xavier Vialard (University Paris-Est) • Marc Niethammer (UNC Chapel Hill)

Subset Selection via Supervised Facility Location

Chengguang Xu (Northeastern University) • Ehsan Elhamifar (Northeastern University)

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

Vincent Sitzmann (Stanford University) • Michael Zollhoefer (Stanford University) • Gordon Wetzstein (Stanford University)

Reconciling λ-Returns with Experience Replay

Brett Daley (Northeastern University) • Christopher Amato (Northeastern University)

Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence

Fengxiang He (The University of Sydney) • Tongliang Liu (The University of Sydney) • Dacheng Tao (University of Sydney)

Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs

Max Simchowitz (Berkeley) • Kevin Jamieson (U Washington)

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation

Mitsuru Kusumoto (Preferred Networks, Inc.) • Takuya Inoue (University of Tokyo) • Gentaro Watanabe (Preferred Networks, Inc.) • Takuya Akiba (Preferred Networks, Inc.) • Masanori Koyama (Preferred Networks Inc. )

Combinatorial Inference against Label Noise

Paul Hongsuck Seo (POSTECH) • Geeho Kim (Seoul National University) • Bohyung Han (Seoul National University)

Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning

Chao Qu (Ant Financial Services Group) • Shie Mannor (Technion) • Huan Xu (Georgia Inst. of Technology) • Yuan Qi (Ant Financial Services Group) • Le Song (Ant Financial Services Group) • Junwu Xiong (Ant Financial Services Group)

Convolution with even-sized kernels and symmetric padding

Shuang Wu (Tsinghua University) • Guanrui Wang (Tsinghua University) • Pei Tang (Tsinghua University) • Feng Chen (Tsinghua University) • Luping Shi (tsinghua university)

On The Classification-Distortion-Perception Tradeoff

Dong Liu (University of Science and Technology of China) • Haochen Zhang (University of Science and Technology of China) • Zhiwei Xiong (University of Science and Technology of China)

Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up

Dominic Richards (University of Oxford) • Patrick Rebeschini (University of Oxford)

Online sampling from log-concave distributions

Holden Lee (Princeton University) • Oren Mangoubi (EPFL) • Nisheeth Vishnoi (Yale University)

Envy-Free Classification

Maria-Florina Balcan (Carnegie Mellon University) • Travis Dick (Carnegie Mellon University) • Ritesh Noothigattu (Carnegie Mellon University) • Ariel D Procaccia (Carnegie Mellon University)

Finding Friend and Foe in Multi-Agent Games

Jack S Serrino (MIT) • Max Kleiman-Weiner (Harvard) • David Parkes (Harvard University) • Josh Tenenbaum (MIT)

Computer Vision with a Single (Robust) Classifier

Shibani Santurkar (MIT) • Andrew Ilyas (MIT) • Dimitris Tsipras (MIT) • Logan Engstrom (MIT) • Brandon Tran (Massachusetts Institute of Technology) • Aleksander Madry (MIT)

Gated CRF Loss for Weakly Supervised Semantic Image Segmentation

Anton Obukhov (ETH Zurich) • Stamatios Georgoulis (ETH Zurich) • Dengxin Dai (ETH Zurich) • Luc V Gool (Computer Vision Lab, ETH Zurich)

Model Compression with Adversarial Robustness: A Unified Optimization Framework

Shupeng Gui (University of Rochester) • Haotao N Wang (Texas A&M University) • Haichuan Yang (University of Rochester) • Chen Yu (University of Rochester) • Zhangyang Wang (TAMU) • Ji Liu (University of Rochester, Tencent AI lab)

Neuron Communication Networks

Jianwei Yang (Georgia Tech) • Zhile Ren (Georgia Tech) • Chuang Gan (MIT-IBM Watson AI Lab) • Hongyuan Zhu (Astar) • Ji Lin (MIT) • Devi Parikh (Georgia Tech / Facebook AI Research (FAIR))

CondConv: Conditionally Parameterized Convolutions for Efficient Inference

Brandon Yang (Google Brain) • Gabriel Bender (Google Brain) • Quoc V Le (Google) • Jiquan Ngiam (Google Brain)

Regression Planning Networks

Danfei Xu (Stanford University) • Roberto Martín-Martín (Stanford University) • De-An Huang (Stanford University) • Yuke Zhu (Stanford University) • Silvio Savarese (Stanford University) • Li Fei-Fei (Stanford University)

Twin Auxilary Classifiers GAN

Mingming Gong (University of Melbourne) • Yanwu Xu (University of Pittsburgh) • Chunyuan Li (Microsoft Research) • Kun Zhang (CMU) • Kayhan Batmanghelich (University of Pittsburgh)

Conditional Structure Generation through Graph Variational Generative Adversarial Nets

Carl Yang (University of Illinois, Urbana Champaign) • Peiye Zhuang (UIUC) • Wenhan Shi (UIUC) • Alan Luu (UIUC) • Pan Li (Stanford)

Distributional Policy Optimization: An Alternative Approach for Continuous Control

Chen Tessler (Technion) • Guy Tennenholtz (Technion) • Shie Mannor (Technion)

Sampling Sketches for Concave Sublinear Functions of Frequencies

Edith Cohen (Google) • Ofir Geri (Stanford University)

Deliberative Explanations: visualizing network insecurities

Pei Wang (UC San Diego) • Nuno Nvasconcelos (UC San Diego)

Computing Full Conformal Prediction Set with Approximate Homotopy

Eugene Ndiaye (Riken AIP) • Ichiro Takeuchi (Nagoya Institute of Technology)

Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift

Stephan Rabanser (Amazon) • Stephan Günnemann (Technical University of Munich) • Zachary Lipton (Carnegie Mellon University)

Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards

Siyuan Li (Tsinghua University) • Rui Wang (Tsinghua University) • Minxue Tang (Tsinghua University) • Chongjie Zhang (Tsinghua University)

Multi-View Reinforcement Learning

Minne Li (University College London) • Lisheng Wu (UCL) • Jun WANG (UCL)

Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution

Thang Vu (KAIST) • Hyunjun Jang (KAIST) • Trung Pham (KAIST) • Chang Yoo (KAIST)

Neural Diffusion Distance for Image Segmentation

Jian Sun (Xi'an Jiaotong University) • Zongben Xu (XJTU)

Fine-grained Optimization of Deep Neural Networks

Mete Ozay (Independent Researcher (N/A))

Extending Stein’s Unbiased Risk Estimator To Train Deep Denoisers with Correlated Pairs of Noisy Images

Magauiya Zhussip (UNIST) • Shakarim Soltanayev (Ulsan National Institute of Science and Technology) • Se Young Chun (UNIST)

Wibergian Learning of Continuous Energy Functions

Chris Russell (The Alan Turing Institute/ The University of Surrey) • Matteo Toso (University of Surrey) • Neill Campbell (University of Bath)

Hyperspherical Prototype Networks

Pascal Mettes (University of Amsterdam) • Elise van der Pol (University of Amsterdam) • Cees Snoek (University of Amsterdam)

Expressive power of tensor-network factorizations for probabilistic modelling

Ivan Glasser (Max Planck Institute of Quantum Optics) • Ryan Sweke (Freie Universitaet Berlin) • Nicola Pancotti (Max Planck Institute of Quantum Optics) • Jens Eisert (Freie Universitaet Berlin) • Ignacio Cirac (Max-Planck Institute of Quantum Optics)

HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs

Naganand Yadati (Indian Institute of Science) • Madhav Nimishakavi (Indian Institute of Science) • Prateek Yadav (Indian Institute of Science) • Vikram Nitin (Indian Institute of Science) • Anand Louis (Indian Institute of Science, Bangalore, India) • Partha Talukdar (Indian Institute of Science, Bangalore)

SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points

Zhize Li (Tsinghua University)

Efficient Meta Learning via Minibatch Proximal Update

Pan Zhou (National University of Singapore) • Xiaotong Yuan (Nanjing University of Information Science & Technology) • Huan Xu (Alibaba Group) • Shuicheng Yan (National University of Singapore) • Jiashi Feng (National University of Singapore)

Unconstrained Monotonic Neural Networks

Antoine Wehenkel (ULiège) • Gilles Louppe (University of Liège)

Guided Similarity Separation for Image Retrieval

Chundi Liu (Layer6 AI) • Guangwei Yu (Layer6) • Maksims Volkovs (layer6.ai) • Cheng Chang (Layer6 AI) • Himanshu Rai (Layer6 AI) • Junwei Ma (Layer6 AI) • Satya Krishna Gorti (Layer6 AI)

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Kaidi Cao (Stanford University) • Colin Wei (Stanford University) • Adrien Gaidon (Toyota Research Institute) • Nikos Arechiga (Toyota Research Institute) • Tengyu Ma (Stanford)

Strategizing against No-regret Learners

Yuan Deng (Duke University) • Jon Schneider (Google Research) • Balasubramanian Sivan (Google Research)

D-VAE: A Variational Autoencoder for Directed Acyclic Graphs

Muhan Zhang (Washington University in St. Louis) • Shali Jiang (Washington University in St. Louis) • Zhicheng Cui (Washington University in St. Louis) • Roman Garnett (Washington University in St. Louis) • Yixin Chen (Washington University in St. Louis)

Hierarchical Optimal Transport for Document Representation

Mikhail Yurochkin (IBM Research, MIT-IBM Watson AI Lab) • Sebastian Claici (MIT) • Edward Chien (Massachusetts Institute of Technology) • Farzaneh Mirzazadeh (IBM Research, MIT-IBM Watson AI Lab) • Justin M Solomon (MIT)

Multivariate Sparse Coding of Nonstationary Covariances with Gaussian Processes

Rui Li (Rochester Institute of Technology)

Positional Normalization

Boyi Li (Cornell University) • Felix Wu (Cornell University) • Kilian Weinberger (Cornell University) • Serge Belongie (Cornell University)

A New Defense Against Adversarial Images: Turning a Weakness into a Strength

Shengyuan Hu (Cornell University) • Tao Yu (Cornell University) • Chuan Guo (Cornell University) • Wei-Lun Chao (Cornell University Ohio State University (OSU)) • Kilian Weinberger (Cornell University)

Quadratic Video Interpolation

Xiangyu Xu (Tsinghua University) • Li Si-Yao (Beijing Normal University) • Wenxiu Sun (SenseTime Research) • Qian Yin (Beijing Normal University) • Ming-Hsuan Yang (UC Merced / Google)

ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies

Bao Wang (UCLA) • Zuoqiang Shi ([email protected]) • Stanley Osher (UCLA)

Incremental Scene Synthesis

Benjamin Planche (Siemens Corporate Technology) • Xuejian Rong (City University of New York) • Ziyan Wu (Siemens Corporation) • Srikrishna Karanam (Siemens Corporate Technology, Princeton) • Harald Kosch (PASSAU) • YingLi Tian (City University of New York) • Jan Ernst (Siemens Research) • ANDREAS HUTTER (Siemens Corporate Technology, Germany)

Self-Supervised Generalisation with Meta Auxiliary Learning

Shikun Liu (Imperial College London) • Andrew Davison (Imperial College London) • Edward Johns (Imperial College London)

Variational Denoising Network: Toward Blind Noise Modeling and Removal

Zongsheng Yue (Xi'an Jiaotong University) • Hongwei Yong (The Hong Kong Polytechnic University) • Qian Zhao (Xi'an Jiaotong University) • Deyu Meng (Xi'an Jiaotong University) • Lei Zhang (The Hong Kong Polytechnic Univ)

Fast Sparse Group Lasso

Yasutoshi Ida (NTT) • Yasuhiro Fujiwara (NTT Software Innovation Center) • Hisashi Kashima (Kyoto University/RIKEN Center for AIP)

Learnable Tree Filter for Structure-preserving Feature Transform

Lin Song (Xi'an Jiaotong University) • Yanwei Li (Institute of Automation, Chinese Academy of Sciences) • Zeming Li (Megvii(Face++) Inc) • Gang Yu (Megvii Inc) • Hongbin Sun (Xi'an Jiaotong University) • Jian Sun (Megvii, Face++) • Nanning Zheng (Xi'an Jiaotong University)

Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis

Yuki Yoshida (The University of Tokyo) • Masato Okada (The University of Tokyo)

Coordinated hippocampal-entorhinal replay as structural inference

Talfan Evans (University College London) • Neil Burgess (University College London)

Cascaded Dilated Dense Network with Two-step Data Consistency for MRI Reconstruction

Hao Zheng (East China Normal University) • Faming Fang (East China Normal University) • Guixu Zhang (East China Normal University)

On the Ineffectiveness of Variance Reduced Optimization for Deep Learning

Aaron Defazio (Facebook AI Research) • Leon Bottou (FAIR)

On the Curved Geometry of Accelerated Optimization

Aaron Defazio (Facebook AI Research)

Multi-marginal Wasserstein GAN

Jiezhang Cao (South China University of Technology) • Langyuan Mo (South China University of Technology) • Yifan Zhang (South China University of Technology) • Kui Jia (South China University of Technology) • Chunhua Shen (University of Adelaide) • Mingkui Tan (South China University of Technology)

Better Exploration with Optimistic Actor Critic

Kamil Ciosek (Microsoft) • Quan Vuong (University of California San Diego) • Robert Loftin (Microsoft Research) • Katja Hofmann (Microsoft Research)

Importance Resampling for Off-policy Prediction

Matthew Schlegel (University of Alberta) • Wesley Chung (University of Alberta) • Daniel Graves (Huawei) • Jian Qian (University of Alberta) • Martha White (University of Alberta)

The Label Complexity of Active Learning from Observational Data

Songbai Yan (University of California, San Diego) • Kamalika Chaudhuri (UCSD) • Tara Javidi (University of California San Diego)

Meta-Learning Representations for Continual Learning

Khurram Javed (University of Alberta) • Martha White (University of Alberta)

Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training

Haichao Zhang (Horizon Robotics) • Jianyu Wang (Baidu USA)

Visualizing the PHATE of Neural Networks

Scott Gigante (Yale University) • Adam S Charles (Princeton University) • Smita Krishnaswamy (Yale University) • Gal Mishne (Yale)

The Cells Out of Sample (COOS) dataset and benchmarks for measuring out-of-sample generalization of image classifiers

Alex X Lu (University of Toronto) • Amy X Lu (University of Toronto/Vector Institute) • Wiebke Schormann (Sunnybrook Research Institute) • David Andrews (Sunnybrook Research Institute) • Alan Moses (University of Toronto)

Nonconvex Low-Rank Tensor Completion from Noisy Data

Changxiao Cai (Princeton University) • Gen Li (Tsinghua University) • H. Vincent Poor (Princeton University) • Yuxin Chen (Princeton University)

Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization

Gautam Goel (Caltech) • Yiheng Lin (Institute for Interdisciplinary Information Sciences, Tsinghua University) • Haoyuan Sun (California Institute of Technology) • Adam Wierman (California Institute of Technology)

Channel Gating Neural Networks

Weizhe Hua (Cornell University) • Yuan Zhou (Cornell) • Christopher De Sa (Cornell) • Zhiru Zhang (Cornell Univeristy) • G. Edward Suh (Cornell University)

Neural networks grown and self-organized by noise

Guruprasad Raghavan (California Institute of Technology) • Matt Thomson (California Institute of Technology)

Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning

Xinyang Chen (Tsinghua University) • Sinan Wang (Tsinghua University) • Bo Fu (Tsinghua University) • Mingsheng Long (Tsinghua University) • Jianmin Wang (Tsinghua University)

Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting

Jun Shu (Xi'an Jiaotong University) • Qi Xie (Xi'an Jiaotong University) • Lixuan Yi (Xi'an Jiaotong University) • Qian Zhao (Xi'an Jiaotong University) • Sanping Zhou (Xi'an Jiaotong University) • Zongben Xu (Xi'an Jiaotong University) • Deyu Meng (Xi'an Jiaotong University)

Variational Structured Semantic Inference for Diverse Image Captioning

Fuhai Chen (Xiamen University) • Rongrong Ji (Xiamen University, China) • Jiayi Ji (Xiamen University) • Xiaoshuai Sun (Xiamen University) • Baochang Zhang (Beihang University) • Xuri Ge (Xiamen University) • Yongjian Wu (Tencent Technology (Shanghai) Co.,Ltd) • Feiyue Huang (Tencent) • Yan Wang (Microsoft)

Mapping State Space using Landmarks for Universal Goal Reaching

Zhiao Huang (University of California San Diego) • Hao Su (University of California San Diego) • Fangchen Liu (UCSD)

Transferable Normalization: Towards Improving Transferability of Deep Neural Networks

Ximei Wang (Tsinghua University) • Ying Jin (Tsinghua University) • Mingsheng Long (Tsinghua University) • Jianmin Wang (Tsinghua University) • Michael Jordan (UC Berkeley)

Random deep neural networks are biased towards simple functions

Giacomo De Palma (Massachusetts Institute of Technology) • Bobak Kiani (Massachusetts Institute of Technology) • Seth Lloyd (MIT)

XNAS: Neural Architecture Search with Expert Advice

Niv Nayman (Alibaba Group) • Asaf Noy (Alibaba) • Tal Ridnik (MIIL Alibaba) • Itamar Friedman (Alibaba) • Jing Rong (Alibaba) • Lihi Zelnik (Alibaba)

CNN^{2}: Viewpoint Generalization via a Binocular Vision

Wei-Da Chen (National Tsing Hua University) • Shan-Hung Wu (National Tsing Hua University)

Generalized Off-Policy Actor-Critic

Shangtong Zhang (University of Oxford) • Wendelin Boehmer (University of Oxford) • Shimon Whiteson (University of Oxford)

DAC: The Double Actor-Critic Architecture for Learning Options

Shangtong Zhang (University of Oxford) • Shimon Whiteson (University of Oxford)

Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models

Tao Yu (Cornell University) • Christopher De Sa (Cornell)

Controlling Neural Level Sets

Matan Atzmon (Weizmann Institute Of Science) • Niv Haim (Weizmann Institute of Science) • Lior Yariv (Weizmann Institute of Science) • Ofer Israelov (Weizmann Institute of Science) • Haggai Maron (Weizmann Institute, Israel) • Yaron Lipman (Weizmann Institute of Science)

Blended Matching Pursuit

Cyrille Combettes (Georgia Institute of Technology) • Sebastian Pokutta (Georgia Institute of Technology)

An Improved Analysis of Training Over-parameterized Deep Neural Networks

Difan Zou (University of California, Los Angeles) • Quanquan Gu (UCLA)

Controllable Text to Image Generation

Bowen Li (University of Oxford) • Xiaojuan Qi (University of Oxford) • Thomas Lukasiewicz (University of Oxford) • Philip Torr (University of Oxford)

Improving Textual Network Learning with Variational Homophilic Embeddings

Wenlin Wang (Duke Univeristy) • Chenyang Tao (Duke University) • Zhe Gan (Microsoft) • Guoyin Wang (Duke University) • Liqun Chen (Duke University) • Xinyuan Zhang (Duke University) • Ruiyi Zhang (Duke University) • Qian Yang (Duke University) • Ricardo Henao (Duke University) • Lawrence Carin (Duke University)

Rethinking Generative Coverage: A Pointwise Guaranteed Approach

Peilin Zhong (Columbia University) • Yuchen Mo (Columbia University) • Chang Xiao (Columbia University) • Pengyu Chen (Columbia University) • Changxi Zheng (Columbia University)

The Randomized Midpoint Method for Log-Concave Sampling

Ruoqi Shen (University of Washington) • Yin Tat Lee (UW)

Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update

Su Young Lee (KAIST) • Choi Sungik (KAIST) • Sae-Young Chung (KAIST)

Fully Neural Network based Model for General Temporal Point Processes

Takahiro Omi (The University of Tokyo) • naonori ueda (RIKEN AIP) • Kazuyuki Aihara (The University of Tokyo)

Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks

Zhonghui You (Peking University) • Kun Yan (Peking University) • Jinmian Ye (SMILE Lab) • Meng Ma (Peking University) • Ping Wang (Peking University)

Discrimination in Online Markets: Effects of Social Bias on Learning from Reviews and Policy Design

Faidra Monachou (Stanford University) • Itai Ashlagi (Stanford)

Provably Powerful Graph Networks

Haggai Maron (Weizmann Institute, Israel) • Heli Ben-Hamu (Weizmann Institute of Science) • Hadar Serviansky (WEIZMANN INSTITUTE OF SCIENCE) • Yaron Lipman (Weizmann Institute of Science)

Order Optimal One-Shot Distributed Learning

Arsalan Sharifnassab (Sharif University of Technology) • Saber Salehkaleybar (Sharif University of Technology) • S. Jamaloddin Golestani (Sharif University of Technology)

Information Competing Process for Learning Diversified Representations

Jie Hu (Xiamen University) • Rongrong Ji (Xiamen University, China) • ShengChuan Zhang (Xiamen University) • Xiaoshuai Sun (Xiamen University) • Qixiang Ye (University of Chinese Academy of Sciences, China) • Chia-Wen Lin (National Tsing Hua University) • Qi Tian (Huawei Noah’s Ark Lab)

GENO -- GENeric Optimization for Classical Machine Learning

Soeren Laue (Friedrich Schiller University Jena / Data Assessment Solutions) • Matthias Mitterreiter (Friedrich Schiller University Jena) • Joachim Giesen (Friedrich-Schiller-Universitat Jena)

Conditional Independence Testing using Generative Adversarial Networks

Alexis Bellot (University of Cambridge) • Mihaela van der Schaar (University of Cambridge, Alan Turing Institute and UCLA)

Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function

Aviv Rosenberg (Tel Aviv University) • Yishay Mansour (Tel Aviv University / Google)

Partitioning Structure Learning for Segmented Linear Regression Trees

Xiangyu Zheng (Peking University) • Song Xi Chen (Peking University)

A Tensorized Transformer for Language Modeling

Xindian Ma (Tianjin University) • Peng Zhang (Tianjin University) • Shuai Zhang (Tianjin University) • Nan Duan (Microsoft Research) • Yuexian Hou (Tianjin University) • Ming Zhou (Microsoft Research) • Dawei Song (Beijing Institute of Technology)

Kernel Stein Tests for Multiple Model Comparison

Jen Ning Lim (Max Planck Institute for Intelligent Systems) • Makoto Yamada (Kyoto University / RIKEN AIP) • Bernhard Schölkopf (MPI for Intelligent Systems) • Wittawat Jitkrittum (Max Planck Institute for Intelligent Systems)

Disentangled behavioural representations

Amir Dezfouli (Data61, CSIRO) • Hassan Ashtiani (McMaster University) • Omar Ghattas (CSIRO) • Richard Nock (Data61, the Australian National University and the University of Sydney) • Peter Dayan (Max Planck Institute for Biological Cybernetics) • Cheng Soon Ong (Data61 and ANU)

More Is Less: Learning Efficient Video Representations by Temporal Aggregation Module

Quanfu Fan (IBM Research) • Chun-Fu Chen (IBM Research) • Hilde Kuehne (University of Bonn) • Marco Pistoia (IBM Research) • David Cox (MIT-IBM Watson AI Lab)

Rethinking the CSC Model for Natural Images

Dror Simon (Technion) • Michael Elad (Technion)

Integrating Generative and Discriminative Sparse Kernel Machines for Multi-class Active Learning

Weishi Shi (Rochester Institute of Technology) • Qi Yu (Rochester Institute of Technology)

Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity

Deepak Pathak (UC Berkeley) • Christopher Lu (UC Berkeley) • Trevor Darrell (UC Berkeley) • Phillip Isola (Massachusetts Institute of Technology) • Alexei Efros (UC Berkeley)

Perceiving the arrow of time in autoregressive motion

Kristof Meding (Max Planck Institute for Intelligent Systems) • Dominik Janzing (Amazon) • Bernhard Schölkopf (MPI for Intelligent Systems) • Felix A. Wichmann (University of Tübingen)

DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections

Ofir Nachum (Google Brain) • Yinlam Chow (DeepMind) • Bo Dai (Google Brain) • Lihong Li (Google Brain)

Hyper-Graph-Network Decoders for Block Codes

Eliya Nachmani (Tel Aviv University and Facebook AI Research) • Lior Wolf (Facebook AI Research)

Large Scale Markov Decision Processes with Changing Rewards

Adrian Rivera Cardoso (Georgia Tech) • He Wang (Georgia Institute of Technology) • Huan Xu (Georgia Inst. of Technology)

Multiview Aggregation for Learning Category-Specific Shape Reconstruction

Srinath Sridhar (Stanford University) • Davis Rempe (Stanford University) • Julien Valentin (Google) • Bouaziz Sofien () • Leonidas J Guibas (stanford.edu)

Semi-Parametric Dynamic Contextual Pricing

Virag Shah (Stanford) • Ramesh Johari (Stanford University) • Jose Blanchet (Stanford University)

Nearly Linear-Time, Deterministic Algorithm for Maximizing (Non-Monotone) Submodular Functions Under Cardinality Constraint

Alan Kuhnle (Florida State University)

Initialization of ReLUs for Dynamical Isometry

Rebekka Burkholz (Harvard University) • Alina Dubatovka (ETH Zurich)

Gradient Information for Representation and Modeling

Jie Ding (University of Minnesota) • Robert Calderbank (Duke University) • Vahid Tarokh (Duke University)

SpiderBoost and Momentum: Faster Variance Reduction Algorithms

Zhe Wang (Ohio State University) • Kaiyi Ji (The Ohio State University) • Yi Zhou (University of Utah) • Yingbin Liang (The Ohio State University) • Vahid Tarokh (Duke University)

Minimax rates of estimating approximate differential privacy

Xiyang Liu (University of Washington) • Sewoong Oh (University of Washington)

Backprop with Approximate Activations for Memory-efficient Network Training

Ayan Chakrabarti (Washington University in St. Louis) • Benjamin Moseley (Carnegie Mellon University)

Training Image Estimators without Image Ground Truth

Zhihao Xia (Washington University in St. Louis) • Ayan Chakrabarti (Washington University in St. Louis)

Deep Structured Prediction for Facial Landmark Detection

Lisha Chen (Rensselaer Polytechnic Institute) • Hui Su (IBM) • Qiang Ji (Rensselaer Polytechnic Institute)

Information-Theoretic Confidence Bounds for Reinforcement Learning

Xiuyuan Lu (Stanford University) • Benjamin Van Roy (Stanford University)

Transfer Anomaly Detection by Inferring Latent Domain Representations

Atsutoshi Kumagai (NTT) • Tomoharu Iwata (NTT) • Yasuhiro Fujiwara (NTT Software Innovation Center)

Total Least Squares Regression in Input Sparsity Time

Huaian Diao (Northeast Normal University) • Zhao Song (Harvard University & University of Washington) • David Woodruff (Carnegie Mellon University) • Xin Yang (University of Washington)

Park: An Open Platform for Learning-Augmented Computer Systems

Hongzi Mao (MIT) • Parimarjan Negi (MIT CSAIL) • Akshay Narayan (MIT CSAIL) • Hanrui Wang (Massachusetts Institute of Technology) • Jiacheng Yang (MIT CSAIL) • Haonan Wang (MIT CSAIL) • Ryan Marcus (MIT CSAIL) • ravichandra addanki (Massachusetts Institute of Technology) • Mehrdad Khani Shirkoohi (MIT) • Songtao He (Massachusetts Institute of Technology) • Vikram Nathan (MIT) • Frank Cangialosi (MIT CSAIL) • Shaileshh Venkatakrishnan (MIT) • Wei-Hung Weng (Massachusetts Institute of Technology) • Song Han (MIT) • Tim Kraska (MIT) • Dr.Mohammad Alizadeh (Massachusetts institute of technology)

Adapting Neural Networks for the Estimation of Treatment Effects

Claudia Shi (Columbia University) • David Blei (Columbia University) • Victor Veitch (Columbia University)

Learning Transferable Graph Exploration

Hanjun Dai (Georgia Tech) • Yujia Li (DeepMind) • Chenglong Wang (University of Washington) • Rishabh Singh (Google Brain) • Po-Sen Huang (DeepMind) • Pushmeet Kohli (DeepMind)

Conformal Prediction Under Covariate Shift

Rina Foygel Barber (University of Chicago) • Emmanuel Candes (Stanford University) • Aaditya Ramdas (CMU) • Ryan Tibshirani (Carnegie Mellon University)

Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation

Chen Dan (Carnegie Mellon University) • Hong Wang (Massachusetts Institute of Technology) • Hongyang Zhang (Carnegie Mellon University) • Yuchen Zhou (University of Wisconsin, Madison) • Pradeep Ravikumar (Carnegie Mellon University)

Asymmetric Valleys: Beyond Sharp and Flat Local Minima

Haowei He (Beihang University) • Gao Huang (Tsinghua) • Yang Yuan (Cornell University)

Positive-Unlabeled Compression on the Cloud

Yixing Xu (Huawei Noah's Ark Lab) • Yunhe Wang (Noah’s Ark Laboratory, Huawei Technologies Co., Ltd.) • Hanting Chen (Peking University) • Kai Han (Huawei Noah's Ark Lab) • Chunjing XU (Huawei Technologies) • Dacheng Tao (University of Sydney) • Chang Xu (University of Sydney)

Direct Estimation of Differential Functional Graphical Model

Boxin Zhao (UChicago) • Sam Wang (UW) • Mladen Kolar (University of Chicago)

On the Calibration of Multiclass Classification with Rejection

Chenri Ni (The University of Tokyo) • Nontawat Charoenphakdee (The University of Tokyo / RIKEN) • Junya Honda (The University of Tokyo / RIKEN) • Masashi Sugiyama (RIKEN / University of Tokyo)

Third-Person Visual Imitation Learning via Decoupled Hierarchical Control

Pratyusha Sharma (Carnegie Mellon University) • Deepak Pathak (UC Berkeley) • Abhinav Gupta (Facebook AI Research/CMU)

Stagewise Training Accelerates Convergence of Testing Error Over SGD

Zhuoning Yuan (UI-Computer Science) • Yan Yan (the University of Iowa) • Jing Rong (Alibaba) • Tianbao Yang (The University of Iowa)

Learning Robust Options by Conditional Value at Risk Optimization

Takuya Hiraoka (NEC) • Takahisa Imagawa (National Institute of Advanced Industrial Science and Technology) • Tatsuya Mori (NEC) • Takashi Onishi (NEC) • Yoshimasa Tsuruoka (The University of Tokyo)

Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems

Yi Xu (The University of Iowa) • Jing Rong (Alibaba) • Tianbao Yang (The University of Iowa)

On Learning Over-parameterized Neural Networks: A Functional Approximation Prospective

Lili Su (MIT) • Pengkun Yang (Princeton University)

Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries

Fuwen Tan (University of Virginia) • Paola Cascante-Bonilla (University of Virginia) • Xiaoxiao Guo (IBM Research) • Hui Wu (IBM Research) • Song Feng (IBM Research) • Vicente Ordonez (University of Virginia)

Visual Sequence Learning in Hierarchical Prediction Networks and Primate Visual Cortex

JIELIN QIU (Shanghai Jiao Tong University) • Ge Huang (Carnegie Mellon University) • Tai Sing Lee (Carnegie Mellon University)

Dual Variational Generation for Low Shot Heterogeneous Face Recognition

Chaoyou Fu (Institute of Automation, Chinese Academy of Sciences) • Xiang Wu (Institue of Automation, Chinese Academy of Science) • Yibo Hu (Institute of Automation, Chinese Academy of Sciences) • Huaibo Huang (Institute of Automation, Chinese Academy of Science) • Ran He (NLPR, CASIA)

Discovering Neural Wirings

Mitchell N Wortsman (University of Washington, Allen Institute for Artificial Intelligence) • Ali Farhadi (University of Washington, Allen Institute for Artificial Intelligence) • Mohammad Rastegari (Allen Institute for Artificial Intelligence (AI2))

On the Optimality of Perturbations in Stochastic and Adversarial Multi-armed Bandit Problems

Baekjin Kim (University of Michigan) • Ambuj Tewari (University of Michigan)

Knowledge Extraction with No Observable Data

Jaemin Yoo (Seoul National University) • Minyong Cho (Seoul National University) • Taebum Kim (Seoul National University) • U Kang (Seoul National University)

PAC-Bayes under potentially heavy tails

Matthew Holland (Osaka University)

One-Shot Object Detection with Co-Attention and Co-Excitation

Ting-I Hsieh (National Tsing Hua University) • Yi-Chen Lo (National Tsing Hua University) • Hwann-Tzong Chen (National Tsing Hua University) • Tyng-Luh Liu (Academia Sinica)

Quaternion Knowledge Graph Embeddings

SHUAI ZHANG (University of New South Wales) • Yi Tay (Nanyang Technological University) • Lina Yao (UNSW) • Qi Liu (Facebook AI Research)

Glyce: Glyph-vectors for Chinese Character Representations

Yuxian Meng (Shannon.AI) • Wei Wu (Shannon.AI) • Fei Wang (Shannon.AI) • Xiaoya Li (Shannon.AI) • Ping Nie (Shannon.AI) • Fan Yin (Shannon.AI) • Muyu Li (Shannon.AI) • Qinghong Han (Shannon.AI) • Xiaofei Sun (Shannon.AI) • Jiwei Li (Shannon.AI)

Turbo Autoencoder: Deep learning based channel code for point-to-point communication channels

Yihan Jiang (University of Washington Seattle) • Hyeji Kim (Samsung AI Center Cambridge) • Himanshu Asnani (University of Washington, Seattle) • Sreeram Kannan (University of Washington) • Sewoong Oh (University of Washington) • Pramod Viswanath (UIUC)

Heterogeneous Graph Learning for Visual Commonsense Reasoning

Weijiang Yu (Sun Yat-sen University) • Jingwen Zhou (Sun Yat-sen University) • Weihao Yu (Sun Yat-sen University) • Xiaodan Liang (Sun Yat-sen University) • Nong Xiao (Sun Yat-sen University)

Probabilistic Watershed: Sampling all spanning forests for seeded segmentation and semi-supervised learning

Enrique Fita Sanmartin (Heidelberg University) • Sebastian Damrich (Heidelberg University) • Fred Hamprecht (Heidelberg University)

Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components

Sascha Saralajew (Dr. Ing. h.c. Porsche AG) • Lars G Holdijk (Radboud University Nijmegen) • Maike Rees (Dr. Ing. h.c. F. Porsche AG) • Ebubekir Asan (Dr. Ing. h.c. F. Porsche AG) • Thomas Villmann (Hochschule Mittweida)

Identifying Causal Effects via Context-specific Independence Relations

Santtu Tikka (University of Jyväskylä) • Antti Hyttinen (University of Helsinki) • Juha Karvanen (University of Jyvaskyla)

Bridging Machine Learning and Logical Reasoning by Abductive Learning

Wang-Zhou Dai (Imperial College London) • Qiuling Xu (Purdue University) • Yang Yu (Nanjing University) • Zhi-Hua Zhou (Nanjing University)

Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function

Zihan Zhang (Tsinghua University) • Xiangyang Ji (Tsinghua University)

On the Global Convergence of (Fast) Incremental Expectation Maximization Methods

Belhal Karimi (Ecole Polytechnique) • Hoi-To Wai (Chinese University of Hong Kong) • Eric Moulines (Ecole Polytechnique) • Marc Lavielle (Inria & Ecole Polytechnique)

A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization

Sulaiman Alghunaim (UCLA) • Kun Yuan (UCLA) • Ali H. Sayed (Ecole Polytechnique Fédérale de Lausanne)

Regularizing Trajectory Optimization with Denoising Autoencoders

Rinu Boney (Aalto University) • Norman Di Palo (Sapienza University of Rome) • Mathias Berglund (Curious AI) • Alexander Ilin (Aalto University) • Juho Kannala (Aalto University) • Antti Rasmus (The Curious AI Company) • Harri Valpola (Curious AI)

Learning Hierarchical Priors in VAEs

Alexej Klushyn (Volkswagen Group) • Nutan Chen (Volkswagen Group) • Richard Kurle (Volkswagen Group) • Botond Cseke (Volkswagen Group) • Patrick van der Smagt (Volkswagen Group)

Epsilon-Best-Arm Identification in Pay-Per-Reward Multi-Armed Bandits

Sivan Sabato (Ben-Gurion University of the Negev)

Safe Exploration for Interactive Machine Learning

Matteo Turchetta (ETH Zurich) • Felix Berkenkamp (ETH Zurich) • Andreas Krause (ETH Zurich)

Addressing Failure Detection by Learning Model Confidence

Charles Corbiere (Valeo.ai) • Nicolas THOME (Cnam) • Avner Bar-Hen (CNAM, Paris) • Matthieu Cord (Sorbonne University) • Patrick Pérez (Valeo.ai)

Combinatorial Bayesian Optimization using the Graph Cartesian Product

Changyong Oh (University of Amsterdam) • Jakub Tomczak (Qualcomm AI Research) • Efstratios Gavves (University of Amsterdam) • Max Welling (University of Amsterdam / Qualcomm AI Research)

Fooling Neural Network Interpretations via Adversarial Model Manipulation

Juyeon Heo (Sungkyunkwan University) • Sunghwan Joo (Sungkyunkwan University) • Taesup Moon (Sungkyunkwan University (SKKU))

On Lazy Training in Differentiable Programming

Lénaïc Chizat (INRIA) • Edouard Oyallon (CentraleSupelec) • Francis Bach (INRIA - Ecole Normale Superieure)

Quality Aware Generative Adversarial Networks

Parimala Kancharla (Indian Institute of Technology, Hyderabad) • Sumohana S Channappayya (Indian Institute of Technology Hyderabad)

Copula-like Variational Inference

Marcel Hirt (University College London) • Petros Dellaportas (University College London, Athens University of Economics and Alan Turing Institute) • Alain Durmus (ENS)

Implicit Regularization for Optimal Sparse Recovery

Tomas Vaskevicius (University of Oxford) • Varun Kanade (University of Oxford) • Patrick Rebeschini (University of Oxford)

Locally Private Gaussian Estimation

Matthew Joseph (University of Pennsylvania) • Janardhan Kulkarni (Microsoft Research) • Jieming Mao (Google Research) • Steven Wu (Microsoft Research)

Multi-mapping Image-to-Image Translation via Learning Disentanglement

Xiaoming Yu (Peking University, Shenzhen Graduate School and Peng Cheng Laboratory) • Yuanqi Chen (SECE, Peking University) • Shan Liu (Tencent) • Thomas Li (Shenzhen Graduate School, Peking University) • Ge Li (SECE, Shenzhen Graduate School, Peking University)

Spatially Aggregated Gaussian Processes with Multivariate Areal Outputs

Yusuke Tanaka (NTT) • Toshiyuki Tanaka (Kyoto University) • Tomoharu Iwata (NTT) • Takeshi Kurashima (NTT Corporation) • Maya Okawa (NTT) • Yasunori Akagi (NTT Service Evolution Laboratories, NTT Corporation) • Hiroyuki Toda (NTT Service Evolution Laboratories, NTT Corporation, Japan)

Structured Decoding for Non-Autoregressive Machine Translation

Zhiqing SUN (Peking University) • Zhuohan Li (UC Berkeley) • Haoqing Wang (Peking University) • Di He (Peking University) • Zi Lin (Peking University) • Zhihong Deng (Peking University)

Learning Temporal Pose Estimation from Sparsely-Labeled Videos

Gedas Bertasius (Facebook Research) • Christoph Feichtenhofer (Facebook AI Research) • Du Tran (Facebook) • Jianbo Shi (University of Pennsylvania) • Lorenzo Torresani (Facebook AI Research)

Greedy InfoMax for Biologically Plausible Self-Supervised Representation Learning

Sindy Löwe (University of Amsterdam) • Peter O'Connor (University of Amsterdam) • Bastiaan Veeling (AMLab - University of Amsterdam)

Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching

Hongteng Xu (Duke University) • Dixin Luo (Duke University) • Lawrence Carin (Duke University)

Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition

Satoshi Tsutsui (Indiana University) • Yanwei Fu (Fudan University, Shanghai; AItrics Inc. Seoul) • David Crandall (Indiana University)

Real-Time Reinforcement Learning

Simon Ramstedt (University of Montreal) • Chris Pal (Montreal Institute for Learning Algorithms, École Polytechnique, Université de Montréal)

Robust Multi-agent Counterfactual Prediction

Alexander Peysakhovich (Facebook) • Christian Kroer (Columbia University) • Adam Lerer (Facebook AI Research)

Approximate Inference Turns Deep Networks into Gaussian Processes

Mohammad Emtiyaz Khan (RIKEN) • Alexander Immer (EPFL) • Ehsan Abedi (EPFL) • Maciej Jan Korzepa (Technical University of Denmark)

Deep Signatures

Patrick Kidger (University of Oxford) • Patric Bonnier (University of Oxford) • Imanol Perez Arribas (University of Oxford) • Cristopher Salvi (University of Oxford) • Terry Lyons (University of Oxford)

Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits

Yogev Bar-On (Tel-Aviv University) • Yishay Mansour (Tel Aviv University / Google)

Convergent Policy Optimization for Safe Reinforcement Learning

Ming Yu (The University of Chicago, Booth School of Business) • Zhuoran Yang (Princeton University) • Mladen Kolar (University of Chicago) • Zhaoran Wang (Northwestern University)

Augmented Neural ODEs

Emilien Dupont (Oxford University) • Arnaud Doucet (Oxford) • Yee Whye Teh (University of Oxford, DeepMind)

Thompson Sampling for Multinomial Logit Contextual Bandits

Min-hwan Oh (Columbia University) • Garud Iyengar (Columbia)

Backpropagation-Friendly Eigendecomposition

Wei Wang (EPFL) • Zheng Dang (Xi'an Jiaotong University) • Yinlin Hu (EPFL) • Pascal Fua (EPFL, Switzerland) • Mathieu Salzmann (EPFL)

FastSpeech: Fast, Robust and Controllable Text to Speech

Yi Ren (Zhejiang University) • Yangjun Ruan (Zhejiang University) • Xu Tan (Microsoft Research) • Tao Qin (Microsoft Research) • Sheng Zhao (Microsoft) • Zhou Zhao (Zhejiang University) • Tie-Yan Liu (Microsoft Research)

Ultrametric Fitting by Gradient Descent

Giovanni Chierchia (ESIEE Paris) • Benjamin Perret (ESIEE/PARIS)

Distinguishing Distributions When Samples Are Strategically Transformed

Hanrui Zhang (Duke University) • Yu Cheng (Duke University) • Vincent Conitzer (Duke University)

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks

Gauthier Gidel (Mila) • Francis Bach (INRIA - Ecole Normale Superieure) • Simon Lacoste-Julien (Mila, Université de Montréal)

Deep Set Prediction Networks

Yan Zhang (University of Southampton) • Jonathon Hare (University of Southampton) • Adam Prugel-Bennett ([email protected])

DppNet: Approximating Determinantal Point Processes with Deep Networks

Zelda Mariet (MIT) • Yaniv Ovadia (Google Inc) • Jasper Snoek (Google Brain)

Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control

Sai Zhang (Harvard University) • Qi Zhang (Amazon) • Jieyu Lin (University of Toronto)

Neural Lyapunov Control

Ya-Chien Chang (University of California, San Diego) • Nima Roohi (University of California San Diego) • Sicun Gao (University of California, San Diego)

Fully Dynamic Consistent Facility Location

Vincent Cohen-Addad (CNRS & Sorbonne Université) • Niklas Oskar D Hjuler (University of Copenhagen) • Nikos Parotsidis (University of Rome Tor Vergata) • David Saulpic (Ecole normale supérieure) • Chris Schwiegelshohn (Sapienza, University of Rome)

A Stickier Benchmark for General-Purpose Language Understanding Systems

Alex Wang (New York University) • Yada Pruksachatkun (New York University) • Nikita Nangia (NYU) • Amanpreet Singh (Facebook) • Julian Michael (University of Washington) • Felix Hill (Google Deepmind) • Omer Levy (Facebook) • Samuel Bowman (New York University)

A Flexible Generative Framework for Graph-based Semi-supervised Learning

Jiaqi Ma (University of Michigan) • Weijing Tang (University of Michigan) • Ji Zhu (University of Michigan) • Qiaozhu Mei (University of Michigan)

Self-normalization in Stochastic Neural Networks

Georgios Detorakis (University of California, Irvine) • Sourav Dutta (Univ. Notre Dame) • Abhishek Khanna (Univ. Notre Dame) • Matthew Jerry (Univ. Notre Dame) • Suman Datta (Univ. Notre Dame) • Emre Neftci (Institute for Neural Computation, UCSD)

Optimal Decision Tree with Noisy Outcomes

Su Jia (CMU) • viswanath nagarajan (Univ Michigan, Ann Arbor) • Fatemeh Navidi (University of Michigan) • R Ravi (CMU)

Meta-Curvature

Eunbyung Park (UNC Chapel Hill) • Junier Oliva (UNC-Chapel Hill)

Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning

Nathan Kallus (Cornell University) • Masatoshi Uehara (Harvard University)

KerGM: Kernelized Graph Matching

Zhen Zhang (WASHINGTON UNIVERSITY IN ST.LOUIS) • Yijian Xiang (Washington University in St. Louis) • Lingfei Wu (IBM Research AI) • Bing Xue (Washington University in St. Louis) • Arye Nehorai (WASHINGTON UNIVERSITY IN ST.LOUIS)

Transfusion: Understanding Transfer Learning for Medical Imaging

Maithra Raghu (Cornell University and Google Brain) • Chiyuan Zhang (Google Brain) • Jon Kleinberg (Cornell University) • Samy Bengio (Google Research, Brain Team)

Adversarial training for free!

Ali Shafahi (University of Maryland) • Mahyar Najibi (University of Maryland) • Mohammad Amin Ghiasi (University of Maryland) • Zheng Xu (Google AI) • John P Dickerson (University of Maryland) • Christoph Studer (Cornell University) • Larry Davis (University of Maryland) • Gavin Taylor (US Naval Academy) • Tom Goldstein (University of Maryland)

Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients

Jun Sun (Zhejiang University) • Tianyi Chen (University of Minnesota) • Georgios Giannakis (University of Minnesota) • Zaiyue Yang (Southern University of Science and Technology)

Implicitly learning to reason in first-order logic

Vaishak Belle (University of Edinburgh) • Brendan Juba (Washington University in St. Louis)

Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods

Kevin Liang (Duke University) • Guoyin Wang (Duke University) • Yitong Li (Duke University) • Ricardo Henao (Duke University) • Lawrence Carin (Duke University)

PC-Fairness: A Unified Framework for Measuring Causality-based Fairness

Yongkai Wu (University of Arkansas) • Lu Zhang (University of Arkanasa) • Xintao Wu (University of Arkansas) • Hanghang Tong (Arizona State University)

Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration

Jianchun Chen (New York University) • Lingjing Wang (New York University) • Xiang Li (New York University) • Yi Fang (New York University)

Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds

Nathan Kallus (Cornell University) • Angela Zhou (Cornell University)

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the XAUC Metric

Nathan Kallus (Cornell University) • Angela Zhou (Cornell University)

HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models

Sharon Zhou (Stanford University) • Mitchell L Gordon (Stanford University) • Ranjay Krishna (Stanford University) • Austin Narcomey (Stanford University) • Li Fei-Fei (Stanford University) • Michael Bernstein (Stanford University)

First order expansion of convex regularized estimators

Pierre Bellec (rutgers) • Arun Kuchibhotla (Wharton Statistics)

Capacity Bounded Differential Privacy

Kamalika Chaudhuri (UCSD) • Jacob Imola (UCSD) • Ashwin Machanavajjhala (Duke)

Universal Boosting Variational Inference

Trevor Campbell (UBC) • Xinglong Li (The University of British Columbia)

SGD on Neural Networks Learns Functions of Increasing Complexity

Dimitris Kalimeris (Harvard) • Gal Kaplun (Harvard University) • Preetum Nakkiran (Harvard) • Ben Edelman (Harvard University) • Tristan Yang (Harvard University) • Boaz Barak (Harvard University) • Haofeng Zhang (Harvard University)

The Landscape of Non-convex Empirical Risk with Degenerate Population Risk

Shuang Li (Colorado School of Mines) • Gongguo Tang (Colorado School of Mines) • Michael B Wakin (Colorado School of Mines)

Making AI Forget You: Data Deletion in Machine Learning

Tony Ginart (Stanford University) • Melody Guan (Stanford University) • Gregory Valiant (Stanford University) • James Zou (Stanford)

Practical Differentially Private Top-k Selection with Pay-what-you-get Composition

David Durfee (Georgia Tech) • Ryan Rogers (LinkedIn)

Conformalized Quantile Regression

Yaniv Romano (Stanford University) • Evan Patterson (Stanford University) • Emmanuel Candes (Stanford University)

Thompson Sampling with Information Relaxation Penalties

Seungki Min (Columbia Business School) • Costis Maglaras (Columbia Business School) • Ciamac C Moallemi (Columbia University)

Deep Generalized Method of Moments for Instrumental Variable Analysis

Andrew Bennett (Cornell University) • Nathan Kallus (Cornell University) • Tobias Schnabel (Cornell University)

Learning Sample-Specific Models with Low-Rank Personalized Regression

Benjamin Lengerich (Carnegie Mellon University) • Bryon Aragam (University of Chicago) • Eric Xing (Petuum Inc. / Carnegie Mellon University)

Dance to Music

Hsin-Ying Lee (University of California, Merced) • Xiaodong Yang (NVIDIA Research) • Ming-Yu Liu (Nvidia Research) • Ting-Chun Wang (NVIDIA) • Yu-Ding Lu (UC Merced) • Ming-Hsuan Yang (UC Merced / Google) • Jan Kautz (NVIDIA)

Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask

Hattie Zhou (Uber) • Janice Lan (Uber AI Labs) • Rosanne Liu (Uber AI Labs) • Jason Yosinski (Uber AI Labs)

Implicit Generation and Modeling with Energy Based Models

Yilun Du (MIT) • Igor Mordatch (OpenAI)

Who Learns? Decomposing Learning into Per-Parameter Loss Contribution

Janice Lan (Uber AI Labs) • Rosanne Liu (Uber AI Labs) • Hattie Zhou (Uber) • Jason Yosinski (Uber AI Labs)

Predicting the Politics of an Image Using Webly Supervised Data

Christopher Thomas (University of Pittsburgh) • Adriana Kovashka (University of Pittsburgh)

Adaptive GNN for Image Analysis and Editing

Lingyu Liang (South China University of Technology) • LianWen Jin (South China University of Technology) • Yong Xu (South China University of Technology)

Ultra Fast Medoid Identification via Correlated Sequential Halving

Tavor Z Baharav (Stanford University) • David Tse (Stanford University)

Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD

PHUONG HA NGUYEN (UCONN) • Lam Nguyen (IBM Thomas J. Watson Research Center) • Marten van Dijk (University of Connecticut)

Asymptotics for Sketching in Least Squares Regression

Edgar Dobriban (Stanford University) • Sifan Liu (Tsinghua University)

MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies

Xue Bin Peng (UC Berkeley) • Michael Chang (University of California, Berkeley) • Grace Zhang (1998) • Pieter Abbeel (UC Berkeley Covariant) • Sergey Levine (UC Berkeley)

Exact inference in structured prediction

Kevin Bello (Purdue University) • Jean Honorio (Purdue University)

Coda: An End-to-End Neural Program Decompiler

Cheng Fu (University of California, San Diego) • Huili Chen (UCSD) • Haolan Liu (UCSD) • Xinyun Chen (UC Berkeley) • Yuandong Tian (Facebook AI Research) • Farinaz Koushanfar (UCSD) • Jishen Zhao (UCSD)

Bat-G net: Bat-inspired High-Resolution 3D Image Reconstruction using Ultrasonic Echoes

Gunpil Hwang (KAIST) • Seohyeon Kim (KAIST) • Hyeon-Min Bae (KAIST)

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates

Sharan Vaswani (Mila, Université de Montréal) • Aaron Mishkin (University of British Columbia) • Issam Laradji (University of British Columbia) • Mark Schmidt (University of British Columbia) • Gauthier Gidel (Mila) • Simon Lacoste-Julien (Mila, Université de Montréal)

Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data

Dominik Linzner (TU Darmstadt) • Michael Schmidt (TU Darmstadt) • Heinz Koeppl (Technische Universität Darmstadt)

Privacy-Preserving Classification of Personal Text Messages with Secure Multi-Party Computation

Devin Reich (University of Washington Tacoma) • Ariel Todoki (University of Washington Tacoma) • Rafael Dowsley (Bar-Ilan University) • Martine De Cock (University of Washington Tacoma) • anderson nascimento (UW)

Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacy

Jonathan Ullman (Northeastern University) • Adam Sealfon (Massachusetts Institute of Technology)

Learning Representations for Time Series Clustering

Qianli Ma (South China University of Technology) • Zheng jiawei (South China University of Technology) • Sen Li (South China University of Technology) • Gary W Cottrell (UCSD)

Variance Reduced Uncertainty Calibration

Ananya Kumar (Stanford University) • Percy Liang (Stanford University) • Tengyu Ma (Stanford)

A Normative Theory for Causal Inference and Bayes Factor Computation in Neural Circuits

Wenhao Zhang (Carnegie Mellon & U. of Pittsburgh) • Si Wu (Peking University) • Brent Doiron (University of Pittsburgh) • Tai Sing Lee (Carnegie Mellon University)

Unsupervised Keypoint Learning for Guiding Class-conditional Video Prediction

Yunji Kim (Yonsei University) • Seonghyeon Nam (Yonsei University) • In Cho (Yonsei University) • Seon Joo Kim (Yonsei University)

Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks

Yiwen Guo (Intel Labs China) • Ziang Yan (Tsinghua University) • Changshui Zhang (Tsinghua University)

Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction

Difan Zou (University of California, Los Angeles) • Pan Xu (University of California, Los Angeles) • Quanquan Gu (UCLA)

Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling

Qitian Wu (Shanghai Jiao Tong University) • Zixuan Zhang (Shanghai Jiao Tong University) • Xiaofeng Gao (Shanghai Jiaotong University) • Junchi Yan (Shanghai Jiao Tong University) • Guihai Chen (Shanghai Jiao Tong University)

Cross-sectional Learning of Extremal Dependence among Financial Assets

Xing Yan (The Chinese University of Hong Kong) • Qi Wu (City University of Hong Kong) • Wen Zhang (JD Finance)

Principal Component Projection and Regression in Nearly Linear Time through Asymmetric SVRG

Yujia Jin (Stanford University) • Aaron Sidford (Stanford)

Compression with Flows via Local Bits-Back Coding

Jonathan Ho (UC Berkeley) • Evan Lohn (University of California, Berkeley) • Pieter Abbeel (UC Berkeley Covariant)

Exact Rate-Distortion in Autoencoders via Echo Noise

Rob Brekelmans (University of Southern Caifornia) • Daniel Moyer (University of Southern California) • Aram Galstyan (USC Information Sciences Inst) • Greg Ver Steeg (University of Southern California)

iSplit LBI: Individualized Partial Ranking with Ties via Split LBI

Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences) • Xinwei Sun (MSRA) • Zhiyong Yang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) • Xiaochun Cao (Chinese Academy of Sciences) • Qingming Huang (University of Chinese Academy of Sciences) • Yuan Yao (Hong Kong Univ. of Science & Technology)

Self-Supervised Active Triangulation for 3D Human Pose Reconstruction

Aleksis Pirinen (Lund University) • Erik Gärtner (Lund University) • Cristian Sminchisescu (LTH)

MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization

Shangyu Chen (Nanyang Technological University, Singapore) • Wenya Wang (Nanyang Technological University) • Sinno Jialin Pan (Nanyang Technological University, Singapore)

Improved Precision and Recall Metric for Assessing Generative Models

Tuomas Kynkäänniemi (NVIDIA; Aalto University) • Tero Karras (NVIDIA) • Samuli Laine (NVIDIA) • Jaakko Lehtinen (NVIDIA & Aalto University) • Timo Aila (NVIDIA Research)

A First-order Algorithmic Framework for Distributionally Robust Logistic Regression

Jiajin Li (The Chinese University of Hong Kong) • Sen Huang (The Chinese University of Hong Kong) • Anthony Man-Cho So (CUHK)

PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph

Yikang LI (The Chinese University of Hong Kong) • Tao Ma (Northwestern Polytechnical University) • Yeqi Bai (Nanyang Technological University) • Nan Duan (Microsoft Research) • Sining Wei (Microsoft Research) • Xiaogang Wang (The Chinese University of Hong Kong)

Concomitant Lasso with Repetitions (CLaR): beyond averaging multiple realizations of heteroscedastic noise

Quentin Bertrand (INRIA) • Mathurin Massias (Inria) • Alexandre Gramfort (INRIA, Université Paris-Saclay) • Joseph Salmon (Université de Montpellier)

Joint Optimization of Tree-based Index and Deep Model for Recommender Systems

Han Zhu (Alibaba Group) • Daqing Chang (Alibaba Group) • Ziru Xu (Alibaba Group) • Pengye Zhang (Alibaba Group) • Xiang Li (Alibaba Group) • Jie He (Alibaba Group) • Han Li (Alibaba Group) • Jian Xu (Alibaba Group) • Kun Gai (Alibaba Group)

Learning Generalizable Device Placement Algorithms for Distributed Machine Learning

ravichandra addanki (Massachusetts Institute of Technology) • Shaileshh Bojja Venkatakrishnan (Massachusetts Institute of Technology) • Shreyan Gupta (MIT) • Hongzi Mao (MIT) • Mohammad Alizadeh (Massachusetts Institute of Technology)

Uncoupled Regression from Pairwise Comparison Data

Liyuan Xu (The University of Tokyo / RIKEN) • Junya Honda () • Gang Niu (RIKEN) • Masashi Sugiyama (RIKEN / University of Tokyo)

Cross Attention Network for Few-shot Classification

Ruibing Hou (Institute of Computing Technology，Chinese Academy) • Hong Chang (Institute of Computing Technology, Chinese Academy of Sciences) • Bingpeng MA (University of Chinese Academy of Sciences) • Shiguang Shan (Chinese Academy of Sciences) • Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)

A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution

Qing Qu (New York University) • Xiao Li (The Chinese University of Hong Kong) • Zhihui Zhu (Johns Hopkins University)

SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models

Linfeng Zhang (Tsinghua University ) • Zhanhong Tan (Tsinghua University) • Jiebo Song (Institute for Interdisciplinary Information Core Technology) • Jingwei Chen (Tsinghua University) • Chenglong Bao (Tsinghua university) • Kaisheng Ma (Tsinghua University)

Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs

Lorenzo Dall'Amico (GIPSA lab) • Romain Couillet (CentralSupélec) • Nicolas Tremblay (CNRS)

Teaching Multiple Concepts to a Forgetful Learner

Anette Hunziker (ETH Zurich and University of Zurich) • Yuxin Chen (Caltech) • Oisin Mac Aodha (California Institute of Technology) • Manuel Gomez Rodriguez (Max Planck Institute for Software Systems) • Andreas Krause (ETH Zurich) • Pietro Perona (California Institute of Technology) • Yisong Yue (Caltech) • Adish Singla (MPI-SWS)

Regularized Weighted Low Rank Approximation

Frank Ban (UC Berkeley) • David Woodruff (Carnegie Mellon University) • Richard Zhang (UC Berkeley)

Practical and Consistent Estimation of f-Divergences

Paul Rubenstein (MPI for IS) • Olivier Bousquet (Google Brain (Zurich)) • Josip Djolonga (Google Research, Brain Team) • Carlos Riquelme (Google Brain) • Ilya Tolstikhin (MPI for Intelligent Systems)

Approximation Ratios of Graph Neural Networks for Combinatorial Problems

Ryoma Sato (Kyoto University) • Makoto Yamada (Kyoto University) • Hisashi Kashima (Kyoto University/RIKEN Center for AIP)

Thinning for Accelerating the Learning of Point Processes

Tianbo Li (Nanyang Technological University) • Yiping Ke (Nanyang Technological University)

A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models

Maxim Kuznetsov (Insilico Medicine) • Daniil Polykovskiy (Insilico Medicine) • Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow) • Alexander Zhebrak (Insilico Medicine)

Differentially Private Markov Chain Monte Carlo

Mikko Heikkilä (University of Helsinki) • Joonas Jälkö (Aalto University) • Onur Dikmen (Halmstad University) • Antti Honkela (University of Helsinki)

Full-Gradient Representation for Neural Network Visualization

Suraj Srinivas (Idiap Research Institute & EPFL) • François Fleuret (Idiap Research Institute)

q-means: A quantum algorithm for unsupervised machine learning

Iordanis Kerenidis (Université Paris Diderot) • Jonas Landman (Université Paris Diderot) • Alessandro Luongo (IRIF - Atos quantum lab) • Anupam Prakash (Université Paris Diderot)

Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints

Sebastian Tschiatschek (Microsoft Research) • Ahana Ghosh (MPI-SWS) • Luis Haug (ETH Zurich) • Rati Devidze (MPI-SWS) • Adish Singla (MPI-SWS)

Limitations of the empirical Fisher approximation

Frederik Kunstner (EPFL) • Philipp Hennig (University of Tübingen and MPI for Intelligent Systems Tübingen) • Lukas Balles (University of Tuebingen)

Flow-based Image-to-Image Translation with Feature Disentanglement

Ruho Kondo (Toyota Central R&D Labs., Inc.) • Keisuke Kawano (Toyota Central R&D Labs., Inc) • Satoshi Koide (Toyota Central R&D Labs.) • Takuro Kutsuna (Toyota Central R&D Labs. Inc.)

Learning dynamic semi-algebraic proofs

Alhussein Fawzi (DeepMind) • Mateusz Malinowski (DeepMind) • Hamza Fawzi (University of Cambridge) • Omar Fawzi (ENS Lyon)

Shape and Time Distorsion Loss for Training Deep Time Series Forecasting Models

Vincent LE GUEN (Conservatoire National des Arts et Métiers) • Nicolas THOME (Cnam)

Understanding attention in graph neural networks

Boris Knyazev (University of Guelph) • Graham W Taylor (University of Guelph) • Mohamed R. Amer (Robust.AI)

Data Cleansing for Models Trained with SGD

Satoshi Hara (Osaka University) • Atsushi Nitanda (The University of Tokyo / RIKEN) • Takanori Maehara (RIKEN AIP)

Curvilinear Distance Metric Learning

Shuo Chen (Nanjing University of Science and Technology) • Lei Luo (Pitt) • Jian Yang (Nanjing University of Science and Technology) • Chen Gong (Nanjing University of Science and Technology) • Jun Li (MIT) • Heng Huang (University of Pittsburgh)

Semantically-Regularized Logic Graph Embeddings

Xie Yaqi (National University of Singapore) • Ziwei Xu (National University of Singapore) • Kuldeep S Meel (National University of Singapore) • Mohan Kankanhalli (National University of Singapore,) • Harold Soh (National University of Singapore)

Modeling Uncertainty by Learning A Hierarchy of Deep Neural Connections

Raanan Y. Rohekar (Intel AI Lab) • Yaniv Gurwicz (Intel AI Lab) • Shami Nisimov (Intel AI Lab) • Gal Novik (Intel AI Lab)

Efficient Graph Generation with Graph Recurrent Attention Networks

Renjie Liao (University of Toronto) • Yujia Li (DeepMind) • Yang Song (Stanford University) • Shenlong Wang (University of Toronto) • Will Hamilton (McGill) • David Duvenaud (University of Toronto) • Raquel Urtasun (Uber ATG) • Richard Zemel (Vector Institute/University of Toronto)

Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms

Mahesh Chandra Mukkamala (Saarland University) • Peter Ochs (Saarland University)

Learning Deep Bilinear Transformation for Fine-grained Image Representation

Heliang Zheng (University of Science and Technology of China) • Jianlong Fu (Microsoft Research) • Zheng-Jun Zha (University of Science and Technology of China) • Jiebo Luo (U. Rochester)

Practical Deep Learning with Bayesian Principles

Kazuki Osawa (Tokyo Institute of Technology) • Siddharth Swaroop (University of Cambridge) • Mohammad Emtiyaz Khan (RIKEN) • Anirudh Jain (Indian Institute of Technology (ISM), Dhanbad) • Runa Eschenhagen (University of Osnabrueck) • Richard E Turner (University of Cambridge) • Rio Yokota (Tokyo Institute of Technology, AIST- Tokyo Tech Real World Big-Data Computation Open Innovation Laboratory (RWBC- OIL), National Institute of Advanced Industrial Science and Technology (AIST))

Training Language GANs from Scratch

Cyprien de Masson d'Autume (Google DeepMind) • Shakir Mohamed (DeepMind) • Mihaela Rosca (Google DeepMind) • Jack Rae (DeepMind, UCL)

Pseudo-Extended Markov chain Monte Carlo

Christopher Nemeth (Lancaster University) • Fredrik Lindsten (Linköping Universituy) • Maurizio Filippone (EURECOM) • James Hensman (PROWLER.io)

Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate

James Jordon (University of Oxford) • Jinsung Yoon (University of California, Los Angeles) • Mihaela van der Schaar (University of Cambridge, Alan Turing Institute and UCLA)

Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters

Alberto Maria Metelli (Politecnico di Milano) • Amarildo Likmeta (Politecnico di Milano) • Marcello Restelli (Politecnico di Milano)

On Adversarial Mixup Resynthesis

Christopher Beckham (Ecole Polytechnique de Montreal) • Sina Honari (Mila & University of Montreal) • Alex Lamb (UMontreal (MILA)) • vikas verma (Aalto University) • Farnoosh Ghadiri (École Polytechnique de Montréal) • R Devon Hjelm (Microsoft Research) • Yoshua Bengio (Mila) • Chris Pal (MILA, Polytechnique Montréal, Element AI)

A Geometric Perspective on Optimal Representations for Reinforcement Learning

Marc Bellemare (Google Brain) • Will Dabney (DeepMind) • Robert Dadashi-Tazehozi (Google Brain) • Adrien Ali Taiga (Google) • Pablo Samuel Castro (Google) • Nicolas Le Roux (Google Brain) • Dale Schuurmans (Google Inc.) • Tor Lattimore (DeepMind) • Clare Lyle (University of Oxford)

Learning New Tricks From Old Dogs: Multi-Source Transfer Learning From Pre-Trained Networks

Joshua Lee (Massachusetts Institute of Technology) • Prasanna Sattigeri (IBM Research) • Gregory Wornell (MIT)

Understanding and Improving Layer Normalization

Jingjing Xu (Peking University) • Xu Sun (Peking University) • Zhiyuan Zhang (Peking University) • Guangxiang Zhao (Peking University) • Junyang Lin (Alibaba Group)

Uncertainty-based Continual Learning with Adaptive Regularization

Hongjoon Ahn (SKKU) • Donggyu Lee (Sungkyunkwan university) • Sungmin Cha (Sungkyunkwan University) • Taesup Moon (Sungkyunkwan University (SKKU))

LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning

Yali Du (University of Technology Sydney) • Lei Han (Rutgers University) • Meng Fang (Tencent) • Ji Liu (University of Rochester, Tencent AI lab) • Tianhong Dai (Imperial College London) • Dacheng Tao (University of Sydney)

U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging

Mathias Perslev (University of Copenhagen) • Michael H Jensen (University of Copehagen) • Sune Darkner (University of Copenhagen, Denmark) • Poul Jørgen Jennum (Danish Center for Sleep Medicine, Rigshospitalet) • Christian Igel (University of Copenhagen)

Massively scalable Sinkhorn distances via the Nyström method

Jason Altschuler (MIT) • Francis Bach (INRIA - Ecole Normale Superieure) • Alessandro Rudi (INRIA, Ecole Normale Superieure) • Jonathan Weed (MIT)

Double Quantization for Communication-Efficient Distributed Optimization

Yue Yu (Tsinghua University) • Jiaxiang Wu (Tencent AI Lab) • Longbo Huang (IIIS, Tsinghua Univeristy)

Globally optimal score-based learning of directed acyclic graphs in high-dimensions

Bryon Aragam (University of Chicago) • Arash Amini (UCLA) • Qing Zhou (UCLA)

Multi-relational Poincaré Graph Embeddings

Ivana Balazevic (University of Edinburgh) • Carl Allen (University of Edinburgh) • Timothy Hospedales (University of Edinburgh)

No-Press Diplomacy: Modeling Multi-Agent Gameplay

Philip Paquette (Université de Montréal - MILA) • Yuchen Lu (University of Montreal) • SETON STEVEN BOCCO (MILA - Université de Montréal) • Max Smith (University of Michigan) • Satya O.-G. (MILA) • Jonathan K. Kummerfeld (University of Michigan) • Joelle Pineau (McGill University) • Satinder Singh (University of Michigan) • Aaron Courville (U. Montreal)

State Aggregation Learning from Markov Transition Data

Yaqi Duan (Princeton University) • Tracy Ke (Harvard University) • Mengdi Wang (Princeton University)

Disentangling Influence: Using disentangled representations to audit model predictions

Charles Marx (Haverford College) • Richard Phillips (Haverford College) • Sorelle Friedler (Haverford College) • Carlos Scheidegger (The University of Arizona) • Suresh Venkatasubramanian (University of Utah)

Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning

David Janz (University of Cambridge) • Jiri Hron (University of Cambridge) • Przemysław Mazur (Wayve) • Katja Hofmann (Microsoft Research) • José Miguel Hernández-Lobato (University of Cambridge) • Sebastian Tschiatschek (Microsoft Research)

Partially Encrypted Deep Learning using Functional Encryption

Theo Ryffel (École Normale Supérieure) • David Pointcheval (École Normale Supérieure) • Francis Bach (INRIA - Ecole Normale Superieure) • Edouard Dufour-Sans (Carnegie Mellon University) • Romain Gay (UC Berkeley)

Decentralized Cooperative Stochastic Bandits

David Martínez-Rubio (University of Oxford) • Varun Kanade (University of Oxford) • Patrick Rebeschini (University of Oxford)

Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem

Gonzalo Mena (Harvard) • Jonathan Weed (MIT)

Efficient Deep Approximation of GMMs

Shirin Jalali (Nokia Bell Labs) • Carl Nuzman (Nokia Bell Labs) • Iraj Saniee (Nokia Bell Labs)

Learning low-dimensional state embeddings and metastable clusters from time series data

Yifan Sun (Carnegie Mellon University) • Yaqi Duan (Princeton University) • Hao Gong (Princeton University) • Mengdi Wang (Princeton University)

Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations

Xu Wang (Shenzhen University) • Jingming He (Shenzhen University) • Lin Ma (Tencent AI Lab)

Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes

Creighton Heaukulani (No Affiliation) • Mark van der Wilk (PROWLER.io)

Kernel Instrumental Variable Regression

Rahul Singh (MIT) • Maneesh Sahani (Gatsby Unit, UCL) • Arthur Gretton (Gatsby Unit, UCL)

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments

Hugo Caselles-Dupré (Flowers Laboaratory (ENSTA ParisTech & INRIA) & Softbank Robotics Europe) • Michael Garcia Ortiz (SoftBank Robotics Europe) • David Filliat (ENSTA)

Fast Efficient Hyperparameter Tuning for Policy Gradient Methods

Supratik Paul (University of Oxford) • Vitaly Kurin (RWTH Aachen University) • Shimon Whiteson (University of Oxford)

Offline Contextual Bayesian Optimization

Ian Char (Carnegie Mellon University) • Youngseog Chung (Carnegie Mellon University) • Willie Neiswanger (Carnegie Mellon University) • Kirthevasan Kandasamy (Carnegie Mellon University) • Oak Nelson (Princeton Plasma Physics Lab) • Mark Boyer (Princeton Plasma Physics Lab) • Egemen Kolemen (Princeton Plasma Physics Lab) • Jeff Schneider (Carnegie Mellon University)

Making the Cut: A Bandit-based Approach to Tiered Interviewing

Candice Schumann (University of Maryland) • Zhi Lang (University of Maryland, College Park) • Jeffrey Foster (Tufts University) • John P Dickerson (University of Maryland)

Unsupervised Scalable Representation Learning for Multivariate Time Series

Jean-Yves Franceschi (Sorbonne Université) • Aymeric Dieuleveut (EPFL) • Martin Jaggi (EPFL)

A state-space model for inferring effective connectivity of latent neural dynamics from simultaneous EEG/fMRI

Tao Tu (Columbia University) • John Paisley (Columbia University) • Stefan Haufe (Charité – Universitätsmedizin Berlin) • Paul Sajda (Columbia University)

End to end learning and optimization on graphs

Bryan Wilder (University of Southern California) • Eric Ewing (University of Southern California) • Bistra Dilkina (University of Southern California) • Milind Tambe (USC)

Game Design for Eliciting Distinguishable Behavior

Fan Yang (Carnegie Mellon University) • Liu Leqi (Carnegie Mellon University) • Yifan Wu (Carnegie Mellon University) • Zachary Lipton (Carnegie Mellon University) • Pradeep Ravikumar (Carnegie Mellon University) • Tom M Mitchell (Carnegie Mellon University) • William Cohen (Google AI)

When does label smoothing help?

Rafael Müller (Google Brain) • Simon Kornblith (Google Brain) • Geoffrey E Hinton (Google & University of Toronto)

Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning

Harsh Gupta (University of Illinois at Urbana-Champaign) • R. Srikant (University of Illinois at Urbana-Champaign) • Lei Ying (ASU)

Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks

Lixin Fan (WeBank AI Lab) • Kam Woh Ng (University of Malaya) • Chee Seng Chan (University of Malaya)

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference

Cole Hurwitz (University of Edinburgh) • Kai Xu (University of Ediburgh) • Akash Srivastava (MIT–IBM Watson AI Lab) • Alessio Buccino (University of Oslo) • Matthias Hennig (University of Edinburgh)

Optimal Sketching for Kronecker Product Regression and Low Rank Approximation

Huaian Diao (Northeast Normal University) • Rajesh Jayaram (Carnegie Mellon University) • Zhao Song (UT-Austin) • Wen Sun (Microsoft Research) • David Woodruff (Carnegie Mellon University)

Distribution-Independent PAC Learning of Halfspaces with Massart Noise

Ilias Diakonikolas (USC) • Themis Gouleakis (MPI) • Christos Tzamos (Microsoft Research)

The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies

Basri Ronen (Weizmann Inst.) • David Jacobs (University of Maryland, USA) • Yoni Kasten (Weizmann Institute) • Shira Kritchman (Weizmann Institute)

Online Learning for Auxiliary Task Weighting for Reinforcement Learning

Xingyu Lin (Carnegie Mellon University) • Harjatin Baweja (CMU) • George Kantor (CMU) • David Held (CMU)

Blocking Bandits

Soumya Basu (University of Texas at Austin) • Rajat Sen (University of Texas at Austin) • Sujay Sanghavi (UT-Austin) • Sanjay Shakkottai (University of Texas at Austin)

Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities

Wei Qian (Cornell Univeristy) • Yuqian Zhang (Cornell University) • Yudong Chen (Cornell University)

Prior-Free Dynamic Auctions with Low Regret Buyers

Yuan Deng (Duke University) • Jon Schneider (Google Research) • Balasubramanian Sivan (Google Research)

On Single Source Robustness in Deep Fusion Models

Taewan Kim (University of Texas at Austin) • Joydeep Ghosh (UT Austin)

Policy Evaluation with Latent Confounders via Optimal Balance

Andrew Bennett (Cornell University) • Nathan Kallus (Cornell University)

Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting

Rajat Sen (University of Texas at Austin) • Hsiang-Fu Yu (Amazon) • Inderjit S Dhillon (UT Austin & Amazon)

Adaptive Cross-Modal Few-shot Learning

Chen Xing (Montreal Institute of Learning Algorithms) • Negar Rostamzadeh (Elemenet AI) • Boris Oreshkin (Element AI) • Pedro O. Pinheiro (Element AI)

Spectral Modification of Graphs for Improved Spectral Clustering

Ioannis Koutis (New Jersey Institute of Technology) • Huong Le (NJIT)

Hyperbolic Graph Convolutional Neural Networks

Zhitao Ying (Stanford University) • Ines Chami (Stanford University) • Christopher Ré (Stanford) • Jure Leskovec (Stanford University and Pinterest)

Cost Effective Active Search

Shali Jiang (Washington University in St. Louis) • Roman Garnett (Washington University in St. Louis) • Benjamin Moseley (Carnegie Mellon University)

Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs

Jian QIAN (INRIA Lille - Sequel Team) • Ronan Fruit (Inria Lille) • Matteo Pirotta (Facebook AI Research) • Alessandro Lazaric (Facebook Artificial Intelligence Research)

Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks

Xiao Sun (IBM) • Jungwook Choi (Hanyang University) • Chia-Yu Chen (IBM research) • Naigang Wang (IBM T. J. Watson Research Center) • Swagath Venkataramani (IBM Research) • Vijayalakshmi (Viji) Srinivasan (IBM TJ Watson) • Xiaodong Cui (IBM T. J. Watson Research Center) • Wei Zhang (IBM T.J.Watson Research Center) • Kailash Gopalakrishnan (IBM Research)

A Stratified Approach to Robustness for Randomly Smoothed Classifiers

Guang-He Lee (MIT) • Yang Yuan (MIT) • Shiyu Chang (IBM T.J. Watson Research Center) • Tommi Jaakkola (MIT)

Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees

Ruqi Zhang (Cornell University) • Christopher De Sa (Cornell)

One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers

Ari Morcos (Facebook AI Research) • Haonan Yu (Facebook AI Research) • Michela Paganini (Facebook) • Yuandong Tian (Facebook AI Research)

Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces

Chuan Guo (Cornell University) • Ali Mousavi (Google Brain) • Xiang Wu (Google) • Daniel Holtmann-Rice (Google Inc) • Satyen Kale (Google) • Sashank Reddi (Google) • Sanjiv Kumar (Google Research)

Fair Algorithms for Clustering

Maryam Negahbani (Dartmouth College) • Deeparnab Chakrabarty (Dartmouth) • Nicolas Flores (Dartmouth College) • Suman Bera (UC Santa Cruz)

Learning Mean-Field Games

Xin Guo (University of California, Berkeley) • Anran Hu (University of Californian, Berkeley (UC Berkeley)) • Renyuan Xu (UC Berkeley) • Junzi Zhang (Stanford University)

SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers

Igor Fedorov (Arm Research) • Ryan Adams (Princeton University) • Matthew Mattina (ARM) • Paul Whatmough (Arm Research)

Deep imitation learning for molecular inverse problems

Eric Jonas (University of Chicago)

Visual Concept-Metaconcept Learning

Chi Han (Tsinghua University) • Jiayuan Mao (MIT) • Chuang Gan (MIT-IBM Watson AI Lab) • Josh Tenenbaum (MIT) • Jiajun Wu (MIT)

Adaptive Video-to-Video Synthesis via Network Weight Generation

Ting-Chun Wang (NVIDIA) • Ming-Yu Liu (Nvidia Research) • Andrew Tao (Nvidia Corporation) • Guilin Liu (NVIDIA) • Bryan Catanzaro (NVIDIA) • Jan Kautz (NVIDIA)

Neural Similarity Learning

Weiyang Liu (Georgia Institute of Technology) • Zhen Liu (Georgia Institute of Technology) • James M Rehg (Georgia Tech) • Le Song (Ant Financial & Georgia Institute of Technology)

Ordered Memory

Yikang Shen (Mila, University of Montreal, MSR Montreal) • Shawn Tan (Mila) • SeyedArian Hosseini (Iran University of Science and Technology) • Zhouhan Lin (MILA) • Alessandro Sordoni (Microsoft Research) • Aaron Courville (U. Montreal)

MixMatch: A Holistic Approach to Semi-Supervised Learning

David Berthelot (Google Brain) • Nicholas Carlini (Google) • Ian Goodfellow (Google Brain) • Nicolas Papernot () • Avital Oliver (Google Brain) • Colin A Raffel (Google Brain)

Deep Multivariate Quantiles for Novelty Detection

Jingjing Wang (University of Waterloo) • Sun Sun (University of Waterloo) • Yaoliang Yu (University of Waterloo)

Fast Parallel Algorithms for Statistical Subset Selection Problems

Sharon Qian (Harvard) • Yaron Singer (Harvard University)

PHYRE: A New Benchmark for Physical Reasoning

Anton Bakhtin (Facebook AI Research) • Laurens van der Maaten (Facebook) • Justin Johnson (Facebook AI Research) • Laura Gustafson (Facebook AI Research) • Ross Girshick (FAIR)

How many variables should be entered in a principal component regression equation?

Ji Xu (Columbia University) • Daniel Hsu (Columbia University)

Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery

Jicong Fan (Cornell University) • Lijun Ding (Cornell University) • Yudong Chen (Cornell University) • Madeleine Udell (Cornell University)

Mutually Regressive Point Processes

Ifigeneia Apostolopoulou (Carnegie Mellon University) • Scott Linderman (Stanford University) • Kyle Miller (Carnegie Mellon University) • Artur Dubrawski (Carnegie Mellon University)

Data-driven Estimation of Sinusoid Frequencies

Gautier Izacard (Ecole Polytechnique) • Sreyas Mohan (NYU) • Carlos Fernandez-Granda (NYU)

E2-Train: Energy-Efficient Deep Network Training with Data-, Model-, and Algorithm-Level Saving

Ziyu Jiang (Texas A&M University) • Yue Wang (Rice University) • Xiaohan Chen (Texas A&M University) • Pengfei Xu (Rice University) • Yang Zhao (Rice University) • Yingyan Lin (Rice University) • Zhangyang Wang (TAMU)

ANODEV2: A Coupled Neural ODE Framework

Tianjun Zhang (University of California, Berkeley) • Zhewei Yao (UC Berkeley) • Amir Gholami (University of California, Berkeley) • Joseph Gonzalez (UC Berkeley) • Kurt Keutzer (EECS, UC Berkeley) • Michael W Mahoney (UC Berkeley) • George Biros (University of Texas at Austin)

Estimating Entropy of Distributions in Constant Space

Jayadev Acharya (Cornell University) • Sourbh Bhadane (Cornell University) • Piotr Indyk (MIT) • Ziteng Sun (Cornell University)

On the Utility of Learning about Humans for Human-AI Coordination

Micah Carroll (UC Berkeley) • Rohin Shah (UC Berkeley) • Mark Ho (UC Berkeley) • Thomas Griffiths (Princeton University) • Sanjit Seshia (UC Berkeley) • Pieter Abbeel (UC Berkeley Covariant) • Anca Dragan (UC Berkeley)

Efficient Regret Minimization Algorithm for Extensive-Form Correlated Equilibrium

Gabriele Farina (Carnegie Mellon University) • Chun Kai Ling (Carnegie Mellon University) • Fei Fang (Carnegie Mellon University) • Tuomas Sandholm (Carnegie Mellon University)

Learning in Generalized Linear Contextual Bandits with Stochastic Delays

Zhengyuan Zhou (Stanford University) • Renyuan Xu (UC Berkeley) • Jose Blanchet (Stanford University)

Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness

Saeed Mahloujifar (University of Virginia) • Xiao Zhang (University of Virginia) • Mohammad Mahmoody (University of Virginia) • David Evans (University of Virginia)

Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions

Gabriele Farina (Carnegie Mellon University) • Christian Kroer (Columbia University) • Tuomas Sandholm (Carnegie Mellon University)

On Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model

Erik Nijkamp (UCLA) • Mitch Hill (UCLA Department of Statistics) • Song-Chun Zhu (UCLA) • Ying Nian Wu (University of California, Los Angeles)

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting

Shiyang Li (UCSB) • Xiaoyong Jin (UCSB) • Yao Xuan (UCSB) • Xiyou Zhou (UCSB) • Wenhu Chen (University of California, Santa Barbara) • Yu-Xiang Wang (UC Santa Barbara) • Xifeng Yan (UCSB)

On the Accuracy of Influence Functions for Measuring Group Effects

Pang Wei W Koh (Stanford University) • Kai-Siang Ang (Stanford University) • Hubert Teo (Stanford University) • Percy Liang (Stanford University)

Face Reconstruction from Voice using Generative Adversarial Networks

Yandong Wen (Carnegie Mellon University) • Bhiksha Raj (Carnegie Mellon University) • Rita Singh (Carnegie Mellon University)

Incremental Few-Shot Learning with Attention Attractor Networks

Mengye Ren (University of Toronto / Uber ATG) • Renjie Liao (University of Toronto) • Ethan Fetaya (University of Toronto) • Richard Zemel (Vector Institute/University of Toronto)

On Testing for Biases in Peer Review

Ivan Stelmakh (Carnegie Mellon University) • Nihar Shah (CMU) • Aarti Singh (CMU)

Learning Disentangled Representation for Robust Person Re-identification

Chanho Eom (Yonsei University) • Bumsub Ham (Yonsei University)

Balancing Efficiency and Fairness in On-Demand Ridesourcing

Nixie Lesmana (Nanyang Technological University) • Xuan Zhang (Shanghai Jiaotong University) • Xiaohui Bei (Nanyang Technological University)

Latent Ordinary Differential Equations for Irregularly-Sampled Time Series

Yulia Rubanova (University of Toronto) • Tian Qi Chen (U of Toronto) • David Duvenaud (University of Toronto)

Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion

Yiqi Zhong (University of Southern California) • Cho-Ying Wu (Univ. of Southern California) • Suya You (US Army Research Laboratory) • Ulrich Neumann (USC)

Input Similarity from the Neural Network Perspective

Guillaume Charpiat (INRIA) • Nicolas Girard (Inria Sophia-Antipolis) • Loris Felardos (INRIA) • Yuliya Tarabalka (Inria Sophia-Antipolis)

Adaptive Sequence Submodularity

Marko Mitrovic (Yale University) • Ehsan Kazemi (Yale) • Moran Feldman (Open University of Israel) • Andreas Krause (ETH Zurich) • Amin Karbasi (Yale)

Weight Agnostic Neural Networks

Adam Gaier (Bonn-Rhein-Sieg University of Applied Sciences) • David Ha (Google Brain)

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction

Daniel Freeman (Google Brain) • David Ha (Google Brain) • Luke Metz (Google Brain)

Reducing the variance in online optimization by transporting past gradients

Sébastien Arnold (USC) • Pierre-Antoine Manzagol (Google) • Reza Harikandeh (UBC) • Ioannis Mitliagkas (Mila & University of Montreal) • Nicolas Le Roux (Google Brain)

Characterizing Bias in Classifiers using Generative Models

Daniel McDuff (Microsoft Research) • Shuang Ma (SUNY Buffalo) • Yale Song (Microsoft) • Ashish Kapoor (Microsoft Research)

Optimal Stochastic and Online Learning with Individual Iterates

Yunwen Lei (Southern University of Science and Technology) • Peng Yang (Southern University of Science and Technology) • Ke Tang (Southern University of Science and Technology) • Ding-Xuan Zhou (City University of Hong Kong)

Policy Learning for Fairness in Ranking

Ashudeep Singh (Cornell University) • Thorsten Joachims (Cornell)

Off-Policy Evaluation of Generalization for Deep Q-Learning in Binary Reward Tasks

Alexander Irpan (Google Brain) • Kanishka Rao (Google) • Konstantinos Bousmalis (DeepMind) • Chris Harris (Google) • Julian Ibarz (Google Inc.) • Sergey Levine (Google)

Regularized Gradient Boosting

Corinna Cortes (Google Research) • Mehryar Mohri (Courant Inst. of Math. Sciences & Google Research) • Dmitry Storcheus (Google Research)

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model

Atilim Gunes Baydin (University of Oxford) • Lei Shao (Intel Corporation) • Wahid Bhimji (Berkeley lab) • Lukas Heinrich (New York University) • Saeid Naderiparizi (University of British Columbia) • Andreas Munk (University of British Columbia) • Jialin Liu (Lawrence Berkeley National Lab) • Bradley J Gram-Hansen (University of Oxford) • Gilles Louppe (University of Liège) • Lawrence Meadows (Intel Corporation) • Philip Torr (University of Oxford) • Victor Lee (Intel Corporation) • Kyle Cranmer (New York University) • Mr. Prabhat (LBL/NERSC) • Frank Wood (University of British Columbia)

Markov Random Fields for Collaborative Filtering

Harald Steck (Netflix)

A Step Toward Quantifying Independently Reproducible Machine Learning Research

Edward Raff (Booz Allen Hamilton)

Scalable Global Optimization via Local Bayesian Optimization

David Eriksson (Uber AI) • Matthias Poloczek (University of Arizona) • Jacob Gardner (Uber AI Labs) • Ryan Turner (Uber AI Labs) • Michael Pearce (Warwick University)

Time-series Generative Adversarial Networks

Jinsung Yoon (University of California, Los Angeles) • Daniel Jarrett (University of Cambridge) • M Van Der Schaar (University of California, Los Angeles)

On Accelerating Training of Transformer-Based Language Models

Qian Yang (Duke University) • Zhouyuan Huo (University of Pittsburgh) • Wenlin Wang (Duke Univeristy) • Lawrence Carin (Duke University)

A Refined Margin Distribution Analysis for Forest Representation Learning

Shen-Huan Lyu (Nanjing University) • Liang Yang (Nanjing University) • Zhi-Hua Zhou (Nanjing University)

Robustness to Adversarial Perturbations in Learning from Incomplete Data

Amir Najafi (Sharif University of Technology) • Shin-ichi Maeda (Preferred Networks) • Masanori Koyama (Preferred Networks Inc. ) • Takeru Miyato (Preferred Networks, Inc.)

Exploring Unexplored Tensor Decompositions for Convolutional Neural Networks

Kohei Hayashi (Preferred Networks) • Taiki Yamaguchi (The University of Tokyo) • Yohei Sugawara (Preferred Networks, Inc.) • Shin-ichi Maeda (Preferred Networks)

An Adaptive Empirical Bayesian Method for Sparse Deep Learning

Wei Deng (Purdue University) • Xiao Zhang (Purdue University) • Faming Liang (Purdue University) • Guang Lin (Purdue University)

Adaptive Influence Maximization with Myopic Feedback

Binghui Peng (Tsinghua University) • Wei Chen (Microsoft Research)

Focused Quantization for Sparse CNNs

Yiren Zhao (University of Cambridge) • Xitong Gao (Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences) • Daniel Bates (University of Cambridge) • Robert Mullins (University of Cambridge) • Cheng-Zhong Xu (University of Macau)

Quantum Embedding of Knowledge for Reasoning

Dinesh Garg (IBM Research - India) • Shajith Ikbal Mohamed (IBM Research AI, India) • Santosh Srivastava (IBM Research AI) • Harit Vishwakarma (IBM Research AI) • Hima Karanam (IBM Research AI) • L Venkat Subramaniam (IBM India Research Lab)

Optimal Best Markovian Arm Identification with Fixed Confidence

Vrettos Moulos (UC Berkeley)

Limiting Extrapolation in Linear Approximate Value Iteration

Andrea Zanette (Stanford University) • Alessandro Lazaric (Facebook Artificial Intelligence Research) • Mykel J Kochenderfer (Stanford University) • Emma Brunskill (Stanford University)

Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model

Andrea Zanette (Stanford University) • Mykel J Kochenderfer (Stanford University) • Emma Brunskill (Stanford University)

Invertible Convolutional Flow

Mahdi Karami (University of Alberta) • Dale Schuurmans (Google) • Jascha Sohl-Dickstein (Google Brain) • Laurent Dinh (Google Research) • Daniel Duckworth (Google Brain)

A Latent Variational Framework for Stochastic Optimization

Philippe Casgrain (University of Toronto)

Topology-Preserving Deep Image Segmentation

Xiaoling Hu (Stony Brook University) • Fuxin Li (Oregon State University) • Dimitris Samaras (Stony Brook University) • Chao Chen (Stony Brook University)

Connective Cognition Network for Directional Visual Commonsense Reasoning

Aming Wu (Tianjin University) • Linchao Zhu (University of Sydney, Technology) • Yahong Han (Tianjin University) • Yi Yang (UTS)

Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms

Vikas Garg (MIT) • Tamar Pichkhadze (MIT)

A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning

Francisco Garcia (University of Massachusetts - Amherst) • Philip Thomas (University of Massachusetts Amherst)

Push-pull Feedback Implements Hierarchical Information Retrieval Efficiently

Xiao Liu (Peking University) • Xiaolong Zou (Peking University) • Zilong Ji (Beijing Normal University) • Gengshuo Tian (Beijing Normal University) • Yuanyuan Mi (Weizmann Institute of Science) • Tiejun Huang (Peking University) • K. Y. Michael Wong (Department of Physics, Hong Kong University of Science and Technology) • Si Wu (Peking University)

Learning Disentangled Representations for Recommendation

Jianxin Ma (Tsinghua University) • Chang Zhou (Alibaba Group) • Peng Cui (Tsinghua University) • Hongxia Yang (Alibaba Group) • Wenwu Zhu (Tsinghua University)

Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

Simon Du (Carnegie Mellon University) • Kangcheng Hou (Zhejiang University) • Ruslan Salakhutdinov (Carnegie Mellon University) • Barnabas Poczos (Carnegie Mellon University) • Ruosong Wang (Carnegie Mellon University) • Keyulu Xu (MIT)

In-Place Near Zero-Cost Memory Protection for DNN

Hui Guan (North Carolina State University) • Lin Ning (NCSU) • Zhen Lin (NCSU) • Xipeng Shen (North Carolina State University) • Huiyang Zhou (NCSU) • Seung-Hwan Lim (Oak Ridge National Laboratory)

Acceleration via Symplectic Discretization of High-Resolution Differential Equations

Bin Shi (UC Berkeley) • Simon Du (Carnegie Mellon University) • Weijie Su (University of Pennsylvania) • Michael Jordan (UC Berkeley)

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Zhilin Yang (Tsinghua University) • Zihang Dai (Carnegie Mellon University) • Yiming Yang (CMU) • Jaime Carbonell (CMU) • Ruslan Salakhutdinov (Carnegie Mellon University) • Quoc V Le (Google)

Comparison Against Task Driven Artificial Neural Networks Reveals Functional Properties in Mouse Visual Cortex

Jianghong Shi (University of Washington) • Eric Shea-Brown (University of Washington) • Michael Buice (Allen Institute for Brain Science)

Mixtape: Breaking the Softmax Bottleneck Efficiently

Zhilin Yang (Tsinghua University) • Thang Luong (Google) • Ruslan Salakhutdinov (Carnegie Mellon University) • Quoc V Le (Google)

Variance Reduced Policy Evaluation with Smooth Function Approximation

Hoi-To Wai (Chinese University of Hong Kong) • Mingyi Hong (University of Minnesota) • Zhuoran Yang (Princeton University) • Zhaoran Wang (Northwestern University) • Kexin Tang (University of Minnesota)

Learning GANs and Ensembles Using Discrepancy

Ben Adlam (Google) • Corinna Cortes (Google Research) • Mehryar Mohri (Courant Inst. of Math. Sciences & Google Research) • Ningshan Zhang (NYU)

Co-Generation with GANs using AIS based HMC

Tiantian Fang (University of Illinois Urbana-Champaign) • Alexander Schwing (University of Illinois at Urbana-Champaign)

AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification

Ronghui You (Fudan University) • Zihan Zhang (Fudan University) • Ziye Wang (Fudan University) • Suyang Dai (Fudan University) • Hiroshi Mamitsuka (Kyoto University) • Shanfeng Zhu (Fudan University)

Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs

Himanshu Sahni (Georgia Institute of Technology) • Toby Buckley (Offworld Inc.) • Pieter Abbeel (University of California, Berkley & OpenAI) • Ilya Kuzovkin (Offworld Inc.)

Abstract Reasoning with Distracting Features

Kecheng Zheng (University of Science and Technology of China) • Zheng-Jun Zha (University of Science and Technology of China) • Wei Wei (Google AI)

Generalized Block-Diagonal Structure Pursuit: Learning Soft Latent Task Assignment against Negative Transfer

Zhiyong Yang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) • Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences) • Yangbangyan Jiang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) • Xiaochun Cao (Chinese Academy of Sciences) • Qingming Huang (University of Chinese Academy of Sciences)

Adversarial Training and Robustness for Multiple Perturbations

Florian Tramer (Stanford University) • Dan Boneh (Stanford University)

Doubly-Robust Lasso Bandit

Gi-Soo Kim (Seoul National University) • Myunghee Cho Paik (Seoul National University)

DM2C: Deep Mixed-Modal Clustering

Yangbangyan Jiang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) • Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences) • Zhiyong Yang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) • Xiaochun Cao (Chinese Academy of Sciences) • Qingming Huang (University of Chinese Academy of Sciences)

MaCow: Masked Convolutional Generative Flow

Xuezhe Ma (Carnegie Mellon University) • Xiang Kong (Carnegie Mellon University) • Shanghang Zhang (Carnegie Mellon University) • Eduard Hovy (Carnegie Mellon University)

Learning by Abstraction: The Neural State Machine for Visual Reasoning

Drew Hudson (Stanford) • Christopher Manning (Stanford University)

Adaptive Gradient-Based Meta-Learning Methods

Mikhail Khodak (CMU) • Maria-Florina Balcan (Carnegie Mellon University) • Ameet Talwalkar (CMU)

Equipping Experts/Bandits with Long-term Memory

Kai Zheng (Peking University) • Haipeng Luo (University of Southern California) • Ilias Diakonikolas (USC) • Liwei Wang (Peking University)

A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning

Wenhao Yang (Peking University) • Xiang Li (Peking University) • Zhihua Zhang (Peking University)

Scalable inference of topic evolution via models for latent geometric structures

Mikhail Yurochkin (IBM Research, MIT-IBM Watson AI Lab) • Zhiwei Fan (University of Wisconsin-Madison) • Aritra Guha (University of Michigan) • Paraschos Koutris (University of Wisconsin-Madison) • XuanLong Nguyen (University of Michigan)

Effective End-to-end Unsupervised Outlier Detection via Inlier Priority of Discriminative Network

Siqi Wang (National University of Defense Technology) • Yijie Zeng (Nanyang Technological University) • Xinwang Liu (National University of Defense Technology) • En Zhu (National University of Defense Technology) • Jianping Yin (Dongguan University of Technology) • Chuanfu Xu (National University of Defense Technology) • Marius Kloft (TU Kaiserslautern)

Deep Active Learning with a Neural Architecture Search

Yonatan Geifman (Technion) • Ran El-Yaniv (Technion)

Efficiently escaping saddle points on manifolds

Christopher Criscitiello (Princeton University) • Nicolas Boumal (Princeton University)

AutoAssist: A Framework to Accelerate Training of Deep Neural Networks

Jiong Zhang (University of Texas at Austin) • Hsiang-Fu Yu (Amazon) • Inderjit S Dhillon (UT Austin & Amazon)

DFNets: Spectral CNNs for Graphs with Feedback-looped Filters

W. O. K. Asiri Suranga Wijesinghe (The Australian National University) • Qing Wang (Australian National University)

Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning

Wonjae Kim (Kakao Corporation) • Yoonho Lee (Kakao Corporation)

Comparing Unsupervised Word Translation Methods Step by Step

Mareike Hartmann (University of Copenhagen) • Yova Kementchedjhieva (University of Copenhagen) • Anders Søgaard (University of Copenhagen)

Learning from Crap Data via Generation

Tianyu Guo (Peking University) • Chang Xu (University of Sydney) • Boxin Shi (Peking University) • Chao Xu (Peking University) • Dacheng Tao (University of Sydney)

Constrained deep neural network architecture search for IoT devices accounting hardware calibration

Florian Scheidegger (IBM Research -- Zurich) • Luca Benini (ETHZ, University of Bologna ) • Costas Bekas (IBM Research GmbH) • A. Cristiano I. Malossi (IBM Research - Zurich)

Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection

Yihe Dong (Microsoft Research) • Sam Hopkins (UC Berkeley) • Jerry Li (Microsoft)

Iterative Least Trimmed Squares for Mixed Linear Regression

Yanyao Shen (UT Austin) • Sujay Sanghavi (UT-Austin)

Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces

Yu Qi (Zhejiang University) • Bin Liu (Nanjing University of Posts and Telecommunications) • Yueming Wang (Zhejiang University) • Gang Pan (Zhejiang University)

Divergence-Augmented Policy Optimization

Qing Wang (Tencent AI Lab) • Yingru Li (The Chinese University of Hong Kong, Shenzhen) • Jiechao Xiong (Tencent AI Lab) • Tong Zhang (Tencent AI Lab)

Intrinsic dimension of data representations in deep neural networks

Alessio Ansuini (International School for Advanced Studies (SISSA)) • Alessandro Laio (International School for Advanced Studies (SISSA)) • Jakob H Macke (Technical University of Munich, Munich, Germany) • Davide Zoccolan (Visual Neuroscience Lab, International School for Advanced Studies (SISSA))

Towards a Zero-One Law for Column Subset Selection

Zhao Song (University of Washington) • David Woodruff (Carnegie Mellon University) • Peilin Zhong (Columbia University)

Compositional De-Attention Networks

Yi Tay (Nanyang Technological University) • Anh Tuan Luu (MIT CSAIL) • Aston Zhang (Amazon AI) • Shuohang Wang (Singapore Management University) • Siu Cheung Hui (Nanyang Technological University)

Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning

Jian Ni (University of Science and Technology of China) • Shanghang Zhang (Carnegie Mellon University) • Haiyong Xie (University of Science and Technology of China)

Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

Zeyuan Allen-Zhu (Microsoft Research) • Yuanzhi Li (Princeton) • Yingyu Liang (University of Wisconsin Madison)

Mining GOLD Samples for Conditional GANs

Sangwoo Mo (KAIST) • Chiheon Kim (Kakao Brain) • Sungwoong Kim (Kakao Brain) • Minsu Cho (POSTECH) • Jinwoo Shin (KAIST; AITRICS)

Deep Model Transferability from Attribution Maps

Jie Song (Zhejiang University) • Yixin Chen (Zhejiang University) • Xinchao Wang (Stevens Institute of Technology) • Chengchao Shen (Zhejiang University) • Mingli Song (Zhejiang University)

Fully Parameterized Quantile Function for Distributional Reinforcement Learning

Derek C Yang (UC San Diego) • Li Zhao (Microsoft Research) • Zichuan Lin (Tsinghua University) • Tao Qin (Microsoft Research) • Jiang Bian (Microsoft) • Tie-Yan Liu (Microsoft Research Asia)

Direct Optimization through argmaxarg⁡max for Discrete Variational Auto-Encoder

Guy Lorberbom (Technion) • Tommi Jaakkola (MIT) • Andreea Gane (Google AI) • Tamir Hazan (Technion)

Distributional Reward Decomposition for Reinforcement Learning

Zichuan Lin (Tsinghua University) • Li Zhao (Microsoft Research) • Derek C Yang (UC San Diego) • Tao Qin (Microsoft Research) • Tie-Yan Liu (Microsoft Research Asia) • Guangwen Yang (Tsinghua University)

L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise

Yilun Xu (Peking University) • Peng Cao (Peking University) • Yuqing Kong (Peking University) • Yizhou Wang (Peking University)

Convergence Guarantees for Adaptive Bayesian Quadrature Methods

Motonobu Kanagawa (EURECOM) • Philipp Hennig (University of Tübingen and MPI for Intelligent Systems Tübingen)

Progressive Augmentation of GANs

Dan Zhang (Bosch Center for Artificial Intelligence) • Anna Khoreva (Bosch Center for AI)

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

Ali Kavis (EPFL) • Yehuda Kfir Levy (ETH) • Francis Bach (INRIA - Ecole Normale Superieure) • Volkan Cevher (EPFL)

Meta-Surrogate Benchmarking for Hyperparameter Optimization

Aaron Klein (Amazon Berlin) • Zhenwen Dai (Spotify) • Frank Hutter (University of Freiburg) • Neil Lawrence (Amazon) • Javier Gonzalez (Amazon)

Learning to Perform Local Rewriting for Combinatorial Optimization

Xinyun Chen (UC Berkeley) • Yuandong Tian (Facebook AI Research)

Anti-efficient encoding in emergent communication

Rahma Chaabouni (LSCP-FAIR) • Eugene Kharitonov (Facebook AI) • Emmanuel Dupoux (Ecole des Hautes Etudes en Sciences Sociales) • Marco Baroni (University of Trento)

Singleshot : a scalable Tucker tensor decomposition

Abraham Traore () • Maxime Berar (Université de Rouen) • Alain Rakotomamonjy (Université de Rouen Normandie Criteo AI Lab)

Neural Machine Translation with Soft Prototype

Yiren Wang (University of Illinois at Urbana-Champaign) • Yingce Xia (Microsoft Research Asia) • Fei Tian (Microsoft Research) • Fei Gao (University of Chinese Academy of Sciences) • Tao Qin (Microsoft Research) • Cheng Xiang Zhai (University of Illinois at Urbana-Champaign) • Tie-Yan Liu (Microsoft Research)

Reliable training and estimation of variance networks

Nicki Skafte Detlefsen (Technical University of Denmark) • Martin Jørgensen (Technical University of Denmark) • Søren Hauberg (Technical University of Denmark)

On the Statistical Properties of Multilabel Learning

Weiwei Liu (Wuhan University)

Bayesian Learning of Sum-Product Networks

Martin Trapp (Graz University of Technology) • Robert Peharz (University of Cambridge) • Hong Ge (University of Cambridge) • Franz Pernkopf (Signal Processing and Speech Communication Laboratory, Graz, Austria) • Zoubin Ghahramani (Uber and University of Cambridge)

Bayesian Batch Active Learning as Sparse Subset Approximation

Robert Pinsler (University of Cambridge) • Jonathan Gordon (University of Cambridge) • Eric Nalisnick (University of Cambridge) • José Miguel Hernández-Lobato (University of Cambridge)

Optimal Sparsity-Sensitive Bounds for Distributed Mean Estimation

zengfeng Huang (Fudan University) • Ziyue Huang (HKUST) • Yilei WANG (The Hong Kong University of Science and Technology) • Ke Yi (" Hong Kong University of Science and Technology, Hong Kong")

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks

Xiaohan Ding (Tsinghua University) • guiguang ding (Tsinghua University, China) • Xiangxin Zhou (Tsinghua University) • Yuchen Guo (Tsinghua University) • Jungong Han (Lancaster University) • Ji Liu (University of Rochester, Tencent AI lab)

Variational Bayesian Decision-making for Continuous Utilities

Tomasz Kuśmierczyk (University of Helsinki) • Joseph Sakaya (University of Helsinki) • Arto Klami (University of Helsinki)

The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks

Ryo Karakida (National Institute of Advanced Industrial Science and Technology) • Shotaro Akaho (AIST) • Shun-ichi Amari (RIKEN)

Single-Model Uncertainties for Deep Learning

Natasa Tagasovska (University of Lausanne) • David Lopez-Paz (Facebook AI Research)

Is Deeper Better only when Shallow is Good?

Eran Malach (Hebrew University Jerusalem Israel) • Shai Shalev-Shwartz (Mobileye & HUJI)

Wasserstein Weisfeiler-Lehman Graph Kernels

Matteo Togninalli (ETH Zürich) • Elisabetta Ghisu (ETH Zurich) • Felipe Llinares-Lopez (ETH Zürich) • Bastian Rieck (MLCB, D-BSSE, ETH Zurich) • Karsten Borgwardt (ETH Zurich)

Domain Generalization via Model-Agnostic Learning of Semantic Features

Qi Dou (Imperial College London) • Daniel Coelho de Castro (Imperial College London) • Konstantinos Kamnitsas (Imperial College London) • Ben Glocker (Imperial College London)

Grid Saliency for Context Explanations of Semantic Segmentation

Lukas Hoyer (Bosch Center for Artificial Intelligence) • Mauricio Munoz (Bosch Center for Artificial Intelligence) • Prateek Katiyar (Bosch Center for Artificial Intelligence) • Anna Khoreva (Bosch Center for AI) • Volker Fischer (Robert Bosch GmbH, Bosch Center for Artificial Intelligence)

First-order methods almost always avoid saddle points: The case of Vanishing step-sizes

Ioannis Panageas (SUTD) • Georgios Piliouras (Singapore University of Technology and Design) • Xiao Wang (Singapore University of Technology and Design)

Maximum Mean Discrepancy Gradient Flow

Michael Arbel (UCL) • Anna Korba (UCL) • Adil SALIM (KAUST) • Arthur Gretton (Gatsby Unit, UCL)

Oblivious Sampling Algorithms for Private Data Analysis

Olga Ohrimenko (Microsoft Research) • Sajin Sasy (University of Waterloo)

Semi-supervisedly Co-embedding Attributed Networks

Zai Qiao Meng (University of Glasgow) • Shangsong Liang (Sun Yat-sen University) • Jinyuan Fang (Sun Yat-sen University) • Teng Xiao (Sun Yat-sen University)

From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI

Roman Beliy (weizmann institute) • Guy Gaziv (Weizmann Institute of Science) • Assaf Hoogi (Weizmann Institute) • Francesca Strappini (Weizmann Institute of Science) • Tal Golan (Columbia University) • Michal Irani (The Weizmann Institute of Science)

Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders

Natasa Tagasovska (University of Lausanne) • Damien Ackerer (Swissquote) • Thibault Vatter (Columbia University)

Nonstochastic Multiarmed Bandits with Unrestricted Delays

Tobias Sommer Thune (University of Copenhagen) • Nicolò Cesa-Bianchi (Università degli Studi di Milano) • Yevgeny Seldin (University of Copenhagen)

BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling

Lars Maaløe (Corti) • Marco Fraccaro (Unumed) • Valentin Liévin (DTU) • Ole Winther (Technical University of Denmark)

Code Generation as Dual Task of Code Summarization

Bolin Wei (Peking University) • Ge Li (Peking University) • Xin Xia (Monash University) • Zhiyi Fu (Key Lab of High Confidence Software Technologies (Peking University), Ministry o) • Zhi Jin (Key Lab of High Confidence Software Technologies (Peking University), Ministry o)

Diffeomorphic Temporal Alignment Networks

Ron Shapira weber (Ben Gurion University) • Matan Eyal (Ben Gurion University) • Nicki Skafte Detlefsen (Technical University of Denmark) • Oren Shriki (Ben-Gurion University of the Negev) • Oren Freifeld (Ben-Gurion University)

Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior

Cheng-Chun Hsu (Academia Sinica) • Kuang-Jui Hsu (Qualcomm) • Chung-Chi Tsai (Qualcomm) • Yen-Yu Lin (National Chiao Tung University) • Yung-Yu Chuang (National Taiwan University)

On the Power and Limitations of Random Features for Understanding Neural Networks

Gilad Yehudai (Weizmann Institute of Science) • Ohad Shamir (Weizmann Institute of Science)

Efficient Pure Exploration in Adaptive Round model

tianyuan jin (University of Science and Technology of China) • Jieming SHI (NATIONAL UNIVERSITY OF SINGAPORE) • Xiaokui Xiao (National University of Singapore) • Enhong Chen (University of Science and Technology of China)

Multi-objects Generation with Amortized Structural Regularization

Taufik Xu (Tsinghua University) • Chongxuan LI (Tsinghua University) • Jun Zhu (Tsinghua University) • Bo Zhang (Tsinghua University)

Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time

Karlis Freivalds (Institute of Mathematics and Computer Science) • Emīls Ozoliņš (Institute of Mathematics and Computer Science) • Agris Šostaks (Institute of Mathematics and Computer Science)

DetNAS: Backbone Search for Object Detection

Yukang Chen (Institute of Automation, Chinese Academy of Sciences) • Tong Yang (Megvii Inc.) • Xiangyu Zhang (Megvii Inc (Face++)) • GAOFENG MENG (Institute of Automation, Chinese Academy of Sciences) • Xinyu Xiao (National Laboratory of Pattern recognition (NLPR), Institute of Automation of Chinese Academy of Sciences (CASIA)) • Jian Sun (Megvii, Face++)

Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates

Adil SALIM (KAUST) • Dmitry Koralev (KAUST) • Peter Richtarik (KAUST)

Fast AutoAugment

Sungbin Lim (Kakao Brain) • Ildoo Kim (Kakao Brain) • Taesup Kim (Mila / Kakao Brain) • Chiheon Kim (Kakao Brain) • Sungwoong Kim (Kakao Brain)

On the Convergence Rate of Training Recurrent Neural Networks in the Overparameterized Regime

Zeyuan Allen-Zhu (Microsoft Research) • Yuanzhi Li (Princeton) • Zhao Song (University of Washington)

Interval timing in deep reinforcement learning agents

Ben Deverett (DeepMind) • Ryan Faulkner (Deepmind) • Meire Fortunato (DeepMind) • Gregory Wayne (Google DeepMind) • Joel Leibo (DeepMind)

Graph-based Discriminators: Sample Complexity and Expressiveness

Roi Livni (Tel Aviv University) • Yishay Mansour (Tel Aviv University / Google)

Large Scale Structure of Neural Network Loss Landscapes

Stanislav Fort (Stanford University) • Stanislaw Jastrzebski (New York University)

Learning Nonsymmetric Determinantal Point Processes

Mike Gartrell (Criteo AI Lab) • Victor-Emmanuel Brunel (ENSAE ParisTech) • Elvis Dohmatob (Criteo) • Syrine Krichene (Google)

Hypothesis Set Stability and Generalization

Dylan Foster (MIT) • Spencer Greenberg (Spark Wave) • Satyen Kale (Google) • Haipeng Luo (University of Southern California) • Mehryar Mohri (Courant Inst. of Math. Sciences & Google Research) • Karthik Sridharan (Cornell University)

Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds

Bo Yang (University of Oxford) • Jianan Wang (DeepMind) • Ronald Clark (Imperial College London) • Qingyong Hu (University of Oxford) • Sen Wang (Heriot-Watt University) • Andrew Markham (University of Oxford) • Niki Trigoni (University of Oxford)

Precision-Recall Balanced Topic Modelling

Seppo Virtanen (Imperial College London) • Mark Girolami (Imperial College London)

Learning Sparse Distributions using Iterative Hard Thresholding

Yibo Zhang (Illinois) • Rajiv Khanna (University of California at Berkeley) • Anastasios Kyrillidis (Rice University ) • Oluwasanmi Koyejo (UIUC)

Discriminative Topic Modeling with Logistic LDA

Iryna Korshunova (Ghent University) • Hanchen Xiong (Twitter) • Mateusz Fedoryszak (Twitter) • Lucas Theis (Twitter)

Quantum Wasserstein Generative Adversarial Networks

Shouvanik Chakrabarti (University of Maryland) • Huang Yiming (University of Maryland & University of Electronic Science and Technology of China) • Tongyang Li (University of Maryland) • Soheil Feizi (University of Maryland, College Park) • Xiaodi Wu (University of Maryland)

Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion

Joan Serrà (Telefónica Research) • Santiago Pascual (Universitat Politècnica de Catalunya) • Carlos Segura Perales (Telefónica Research)

Hyperparameter Learning via Distributional Transfer

Ho Chung Law (University of Oxford) • Peilin Zhao (Tencent AI Lab) • Lucian Chan (University of Oxford) • Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) • Dino Sejdinovic (University of Oxford)

Discriminator optimal transport

Akinori Tanaka (RIKEN)

High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes

David Salinas (Amazon) • Michael Bohlke-Schneider (Amazon) • Laurent Callot (Amazon) • Jan Gasthaus (Amazon.com) • Roberto Medico (Amazon AWS)

Are Anchor Points Really Indispensable in Label-Noise Learning?

Xiaobo Xia (Xidian University) • Tongliang Liu (The University of Sydney) • Nannan Wang (Xidian University) • Bo Han (RIKEN) • Chen Gong (Nanjing University of Science and Technology) • Gang Niu (RIKEN) • Masashi Sugiyama (RIKEN / University of Tokyo)

Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations

Fenglin Liu (Peking University) • Yuanxin Liu (Institute of Information Engineering, Chinese Academy of Sciences) • Xuancheng Ren (Peking University) • Xiaodong He (JD AI research) • Kai Lei (peking university) • Xu Sun (Peking University)

Differentiable Sorting using Optimal Transport: The Sinkhorn CDF and Quantile Operator

Marco Cuturi (Google and CREST/ENSAE) • Olivier Teboul (Google Brain) • Jean-Philippe Vert ()

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks

Gaël Letarte (Université Laval) • Pascal Germain (INRIA) • Benjamin Guedj (Inria & University College London) • Francois Laviolette (Université Laval)

Likelihood-Free Overcomplete ICA and ApplicationsIn Causal Discovery

Chenwei DING (The University of Sydney) • Mingming Gong (University of Melbourne) • Kun Zhang (CMU) • Dacheng Tao (University of Sydney)

Interior-point Methods Strike Back: Solving the Wasserstein Barycenter Problem

DongDong Ge (Shanghai University of Finance and Economics) • Haoyue Wang (Fudan University) • Zikai Xiong (Fudan University) • Yinyu Ye (Standord)

Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs

Denis Mazur (Yandex) • Vage Egiazarian (Skoltech) • Stanislav Morozov (Yandex) • Artem Babenko (Yandex)

Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections

Boris Muzellec (ENSAE, Institut Polytechnique de Paris) • Marco Cuturi (Google and CREST/ENSAE)

Efficient Non-Convex Stochastic Compositional Optimization Algorithm via Stochastic Recursive Gradient Descent

Huizhuo Yuan (Peking University) • Xiangru Lian (University of Rochester) • Chris Junchi Li (Tencent AI Lab) • Ji Liu (University of Rochester, Tencent AI lab)

On the convergence of single-call stochastic extra-gradient methods

Yu-Guan Hsieh (École normale supérieure, Paris) • Franck Iutzeler (Univ. Grenoble Alpes) • Jérôme Malick (CNRS and LJK) • Panayotis Mertikopoulos (CNRS (French National Center for Scientific Research))

Infra-slow brain dynamics as a marker for cognitive function and decline

Shagun Ajmera (Indian Institute of Science) • Shreya Rajagopal (Indian Institute of Science) • Razi Rehman (Indian Institute of Science) • Devarajan Sridharan (Indian Institute of Science)

Robust Principle Component Analysis with Adaptive Neighbors

Rui Zhang (Northwestern Polytechincal University) • Hanghang Tong (IBM Research)

High-Quality Self-Supervised Deep Image Denoising

Samuli Laine (NVIDIA) • Tero Karras (NVIDIA) • Jaakko Lehtinen (NVIDIA & Aalto University) • Timo Aila (NVIDIA Research)

Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup

Sebastian Goldt (Institut de Physique théorique, Paris) • Madhu Advani (Harvard University) • Andrew Saxe (University of Oxford) • Florent Krzakala (École Normale Supérieure) • Lenka Zdeborová (CEA Saclay)

GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs

Yuan Liu (Zhejiang University) • Zehong Shen (Zhejiang University) • Zhixuan Lin (Zhejiang University) • Sida Peng (Zhejiang University) • Hujun Bao (Zhejiang University) • Xiaowei Zhou (Zhejiang Univ., China)

Online Prediction of Switching Graph Labelings with Cluster Specialists

Mark Herbster (University College London) • James Robinson (UCL)

Graph-Based Semi-Supervised Learning with Non-ignorable Non-response

Fan Zhou (Shanghai University of Finance and Economics) • Tengfei Li (UNC Chapel Hill) • Haibo Zhou (University of North Carolina at Chapel Hill) • Hongtu Zhu (UNC Chapel Hill) • Ye Jieping (DiDi Chuxing)

BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning

Andreas Kirsch (University of Oxford) • Joost van Amersfoort (University of Oxford) • Yarin Gal (University of Oxford)

A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off

Yaniv Blumenfeld (Technion) • Dar Gilboa (Columbia University) • Daniel Soudry (Technion)

Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs

Marek Petrik (University of New Hampshire) • Reazul Hasan Russel (University of New Hampshire)

Cross-lingual Language Model Pretraining

Alexis CONNEAU (Facebook) • Guillaume Lample (Facebook AI Research)

Approximate Bayesian Inference for a Mechanistic Model of Vesicle Release at a Ribbon Synapse

Cornelius Schröder (University of Tübingen) • Ben James (University of Sussex) • Leon Lagnado (University of Sussex) • Philipp Berens (University of Tübingen)

Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input

Maxence Ernoult (Université Paris Sud) • Benjamin Scellier () • Yoshua Bengio (Mila) • Damien Querlioz (Univ Paris-Sud) • Julie Grollier (Unité Mixte CNRS/Thalès)

Universal Invariant and Equivariant Graph Neural Networks

Nicolas Keriven (Ecole Normale Supérieure) • Gabriel Peyré (CNRS and ENS)

The bias of the sample mean in multi-armed bandits can be positive or negative

Jaehyeok Shin (Carnegie Mellon University) • Aaditya Ramdas (Carnegie Mellon University) • Alessandro Rinaldo (CMU)

On the Correctness and Sample Complexity of Inverse Reinforcement Learning

Abi Komanduru (Purdue University) • Jean Honorio (Purdue University)

VIREL: A Variational Inference Framework for Reinforcement Learning

Matthew Fellows (University of Oxford) • Anuj Mahajan (University of Oxford) • Tim G. J. Rudner (University of Oxford) • Shimon Whiteson (University of Oxford)

First Order Motion Model for Image Animation

Aliaksandr Siarohin (University of Trento) • Stephane Lathuillere (University of Trento) • Sergey Tulyakov (Snap Inc) • Elisa Ricci (FBK - Technologies of Vision) • Nicu Sebe (University of Trento)

Tensor Monte Carlo: Particle Methods for the GPU era

Laurence Aitchison (University of Cambridge)

Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction

Alban Laflaquière (ISIR) • Michael Garcia Ortiz (SoftBank Robotics Europe)

Learning from Label Proportions with Generative Adversarial Networks

Jiabin Liu (University of Chinese Academy of Sciences) • Bo Wang (University of International Business and Economics) • Zhiquan Qi (University of Chinese Academy of Sciences) • YingJie Tian (University of Chinese Academy of Sciences) • Yong Shi (University of Chinese Academy of Sciences)

Efficient and Thrifty Voting by Any Means Necessary

Debmalya Mandal (Columbia University) • Ariel D Procaccia (Carnegie Mellon University) • Nisarg Shah (University of Toronto) • David Woodruff (Carnegie Mellon University)

PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation

Can Qin (Northeastern University) • Haoxuan You (Columbia University) • Lichen Wang (Northeastern University) • C.-C. Jay Kuo (University of Southern California) • Yun Fu (Northeastern University)

ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization

Xiangyi Chen (University of Minnesota) • Sijia Liu (MIT-IBM Watson AI Lab, IBM Research AI) • Kaidi Xu (Northeastern University) • Xingguo Li (Princeton University) • Xue Lin (Northeastern University) • Mingyi Hong (University of Minnesota) • David Cox (MIT-IBM Watson AI Lab)

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning

Erwan Lecarpentier (Université de Toulouse, ONERA The French Aerospace Lab) • Emmanuel Rachelson (ISAE-SUPAERO / University of Toulouse)

Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning

Akihiro Kishimoto (IBM Research) • Beat Buesser (IBM Research) • Bei Chen (IBM Research) • Adi Botea (IBM Research)

Toward a Characterization of Loss Functions for Distribution Learning

Nika Haghtalab (Microsoft) • Cameron Musco (Microsoft Research) • Bo Waggoner (U. Colorado, Boulder)

Coresets for Archetypal Analysis

Sebastian Mair (Leuphana University) • Ulf Brefeld (Leuphana)

Emergence of Object Segmentation in Perturbed Generative Models

Adam Bielski (University of Bern) • Paolo Favaro (Bern University, Switzerland)

Optimal Sparse Decision Trees

Xiyang Hu (Duke University) • Cynthia Rudin (Duke) • Margo Seltzer (University of British Columbia)

Escaping from saddle points on Riemannian manifolds

Yue Sun (University of Washington) • Nicolas Flammarion (UC Berkeley) • Maryam Fazel (University of Washington)

Muti-source Domain Adaptation for Semantic Segmentation

Sicheng Zhao (University of California Berkeley) • Bo Li (Harbin Institute of Technology) • Xiangyu Yue (UC Berkeley) • Yang Gu (Didi chuxing) • Pengfei Xu (Didi Chuxing) • Runbo Hu (DiDi Chuxing) • Hua Chai (Didi Chuxing) • Kurt Keutzer (EECS, UC Berkeley)

Localized Structured Prediction

Carlo Ciliberto (Imperial College London) • Francis Bach (INRIA - Ecole Normale Superieure) • Alessandro Rudi (INRIA, Ecole Normale Superieure)

Nonzero-sum Adversarial Hypothesis Testing Games

Sarath Yasodharan (Indian Institute of Science) • Patrick Loiseau (Inria)

Manifold-regression to predict from MEG/EEG brain signals without source modeling

David Sabbagh (INRIA) • Pierre Ablin (Inria) • Gael Varoquaux (Parietal Team, INRIA) • Alexandre Gramfort (INRIA, Université Paris-Saclay) • Denis A. Engemann (INRIA Saclay)

Modeling Tabular data using Conditional GAN

Lei Xu (MIT) • Maria Skoularidou (University of Cambridge) • Alfredo Cuesta Infante (Universidad Rey Juan Carlos) • Kalyan Veeramachaneni (Massachusetts Institute of Technology)

Normalization Helps Training of Quantized LSTM

Lu Hou (Huawei Technologies Co., Ltd) • Jinhua Zhu (University of Science and Technology of China) • James Kwok (Hong Kong University of Science and Technology) • Fei Gao (University of Chinese Academy of Sciences) • Tao Qin (Microsoft Research) • Tie-Yan Liu (Microsoft Research)

Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration

Clarice Poon (University of Bath) • Jingwei Liang (DAMTP, University of Cambridge)

Deep Scale-spaces: Equivariance Over Scale

Daniel Worrall (University of Amsterdam) • Max Welling (University of Amsterdam / Qualcomm AI Research)

GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series

Edward De Brouwer (KU Leuven) • Jaak Simm (KU Leuven) • Adam Arany (University of Leuven) • Yves Moreau (KU Leuven)

Estimating Convergence of Markov chains with L-Lag Couplings

Niloy Biswas (Harvard University) • Pierre E Jacob (Harvard University)

Learning-Based Low-Rank Approximations

Piotr Indyk (MIT) • Ali Vakilian (Massachusetts Institute of Technology) • Yang Yuan (Cornell University)

Implicit Regularization in Deep Matrix Factorization

Sanjeev Arora (Princeton University) • Nadav Cohen (Tel Aviv University) • Wei Hu (Princeton University) • Yuping Luo (Princeton University)

List-decodable Linear Regression

Sushrut Karmalkar (The University of Texas at Austin) • Adam Klivans (UT Austin) • Pravesh Kothari (Princeton University and Institute for Advanced Study)

Learning elementary structures for 3D shape generation and matching

Theo Deprelle (École des ponts ParisTech) • Thibault Groueix (École des ponts ParisTech) • Matthew Fisher (Adobe Research) • Vladimir Kim (Adobe) • Bryan Russell (Adobe) • Mathieu Aubry (École des ponts ParisTech)

On the Hardness of Robust Classification

Pascale Gourdeau (University of Oxford) • Varun Kanade (University of Oxford) • Marta Kwiatkowska (University of Oxford) • James Worrell (University of Oxford)

Foundations of Comparison-Based Hierarchical Clustering

Debarghya Ghoshdastidar (University of Tübingen) • Michaël Perrot (Max Planck Institute for Intelligent Systems) • Ulrike von Luxburg (University of Tübingen)

What the Vec? Towards Probabilistically Grounded Embeddings

Carl Allen (University of Edinburgh) • Ivana Balazevic (University of Edinburgh) • Timothy Hospedales (University of Edinburgh)

Minimizers of the Empirical Risk and Risk Monotonicity

Marco Loog (Delft University of Technology) • Tom Viering (Delft University of Technology, Netherlands) • Alexander Mey (TU Delft)

Explicit Planning for Efficient Exploration in Reinforcement Learning

Liangpeng Zhang (University of Birmingham) • Xin Yao (University of Birmingham)

Lower Bounds on Adversarial Robustness from Optimal Transport

Arjun Nitin Bhagoji (Princeton University) • Daniel Cullina (Princeton University) • Prateek Mittal (Princeton University)

Neural Spline Flows

Conor Durkan (University of Edinburgh) • Arturs Bekasovs (University of Edinburgh) • Iain Murray (University of Edinburgh) • George Papamakarios (DeepMind)

Phase Transitions and Cyclic Phenomena in Bandits with Switching Constraints

David Simchi-Levi (MIT) • Yunzong Xu (MIT)

Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization

Koen Helwegen (Plumerai) • James Widdicombe (Plumerai) • Lukas Geiger (Plumerai) • Zechun Liu (HKUST) • Kwang-Ting Cheng (Hong Kong University of Science and Technology) • Koen Helwegen (Plumerai)

Nonlinear scaling of resource allocation in sensory bottlenecks

Laura R Edmondson (University of Sheffield) • Alejandro Jimenez Rodriguez (University of Sheffield) • Hannes P. Saal (University of Sheffield)

Constrained Reinforcement Learning: A Dual Approach

Santiago Paternain (University of Pennsylvania) • Luiz Chamon (University of Pennsylvania) • Miguel Calvo-Fullana (University of Pennsylvania) • Alejandro Ribeiro (University of Pennsylvania)

Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules

Niklas Gebauer (Technische Universität Berlin) • Michael Gastegger (Technische Universität Berlin) • Kristof Schütt (TU Berlin)

An adaptive nearest neighbor rule for classification

Akshay Balsubramani (Stanford) • Sanjoy Dasgupta (UC San Diego) • yoav S Freund (UCSD) • Shay Moran (IAS, Princeton)

Coresets for Clustering with Fairness Constraints

Lingxiao Huang (EPFL) • Shaofeng H.-C. Jiang (Weizmann Institute of Science) • Nisheeth Vishnoi (Yale University)

PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments

Ben Graham (Facebook Research) • David Novotny (Facebook AI Research) • Jeremy Reizenstein (Facebook AI Research)

MAVEN: Multi-Agent Variational Exploration

Anuj Mahajan (University of Oxford) • Tabish Rashid (University of Oxford) • Mikayel Samvelyan (Russian-Armenian University) • Shimon Whiteson (University of Oxford)

Competitive Gradient Descent

Florian Schaefer (Caltech) • Anima Anandkumar (NVIDIA / Caltech)

Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses

Ulysse Marteau-Ferey (INRIA) • Francis Bach (INRIA - Ecole Normale Superieure) • Alessandro Rudi (INRIA, Ecole Normale Superieure)

Continual Unsupervised Representation Learning

Dushyant Rao (DeepMind) • Francesco Visin (DeepMind) • Andrei Rusu (DeepMind) • Razvan Pascanu (Google DeepMind) • Yee Whye Teh (University of Oxford, DeepMind) • Raia Hadsell (DeepMind)

Self-Routing Capsule Networks

Taeyoung Hahn (SNUVL) • Myeongjang Pyeon (Seoul National University) • Gunhee Kim (Seoul National University)

The Parameterized Complexity of Cascading Portfolio Scheduling

Eduard Eiben (University of Bergen) • Robert Ganian (TU Wien) • Iyad Kanj (DePaul University, Chicago) • Stefan Szeider (Vienna University of Technology)

Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards

Zhongtian Dai (Toyota Technological Institute at Chicago) • Matthew R. Walter (TTI-Chicago)

Bipartite expander Hopfield networks as self-decoding high-capacity error correcting codes

Rishidev Chaudhuri (University of California, Davis) • Ila Fiete (University of Texas at Austin)

Sequence Modelling with Unconstrained Generation Order

Dmitriy Emelyanenko (Yandex; National Research University Higher School of Economics) • Elena Voita (Yandex; University of Amsterdam) • Pavel Serdyukov (Yandex)

Probabilistic Logic Neural Networks for Reasoning

Meng Qu (MILA) • Jian Tang (HEC Montreal & MILA)

A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families

Brian Axelrod (Stanford) • Ilias Diakonikolas (USC) • Alistair Stewart (University of Southern California) • Anastasios Sidiropoulos (University of Illinois at Chicago) • Gregory Valiant (Stanford University)

A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarsening

Gecia Bravo Hermsdorff (Princeton University) • Lee Gunderson (Princeton University)

Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond

Xuechen Li (Google) • Yi Wu (University of Toronto & Vector Institute) • Lester Mackey (Microsoft Research) • Murat Erdogdu (University of Toronto)

The Implicit Bias of AdaGrad on Separable Data

Qian Qian (the Ohio State University) • Xiaoyuan Qian (Dalian University of Technology)

On two ways to use determinantal point processes for Monte Carlo integration

Guillaume Gautier (CNRS, INRIA, Univ. Lille) • Rémi Bardenet (University of Lille) • Michal Valko (DeepMind Paris and Inria Lille - Nord Europe)

LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition

Zuxuan Wu (UMD) • Caiming Xiong (Salesforce) • Yu-Gang Jiang (Fudan University) • Larry Davis (University of Maryland)

How degenerate is the parametrization of neural networks with the ReLU activation function?

Dennis Elbrächter (University of Vienna) • Julius Berner (University of Vienna) • Philipp Grohs (University of Vienna)

Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks

Wenrui Zhang (Texas A&M University) • Peng Li (Texas A&M University)

Re-examination of the Role of Latent Variables in Sequence Modeling

Guokun Lai (Carnegie Mellon University) • Zihang Dai (Carnegie Mellon University)

Max-value Entropy Search for Multi-Objective Bayesian Optimization

Syrine Belakaria (Washington State University) • Aryan Deshwal (Washington State University) • Janardhan Rao Doppa (Washington State University)

Stein Variational Gradient Descent With Matrix-Valued Kernels

Dilin Wang (UT Austin) • Ziyang Tang (UT Austin) • Chandrajit Bajaj (The University of Texas at Austin) • Qiang Liu (UT Austin)

Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms

Shahana Ibrahim (Oregon State University) • Xiao Fu (Oregon State University) • Nikolaos Kargas (University of Minnesota) • Kejun Huang (University of Florida)

Detecting Overfitting via Adversarial Examples

Roman Werpachowski (DeepMind) • András György (DeepMind) • Csaba Szepesvari (DeepMind/University of Alberta)

A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment

Felix Leibfried (PROWLER.io) • Sergio Pascual-Diaz (PROWLER.io) • Jordi Grau-Moya (PROWLER.io)

SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies

Seyed Kamyar Seyed Ghasemipour (University of Toronto) • Shixiang (Shane) Gu (Google Brain) • Richard Zemel (Vector Institute/University of Toronto)

Towards Understanding the Importance of Shortcut Connections in Residual Networks

Tianyi Liu (Georgia Institute of Technolodgy) • Minshuo Chen (Georgia Tech) • Mo Zhou (Duke University) • Simon Du (Carnegie Mellon University) • Enlu Zhou (Georgia Institute of Technology) • Tuo Zhao (Gatech)

Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains

Elliot Meyerson (Cognizant) • Risto Miikkulainen (The University of Texas at Austin; Cognizant)

Solving Interpretable Kernel Dimensionality Reduction

Chieh T Wu (Northeastern University) • Jared Miller (Northeastern University) • Yale Chang (Northeastern University) • Mario Sznaier (Northeastern University) • Jennifer G Dy (Northeastern University)

Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space

Shuo Yang (UT Austin) • Yanyao Shen (UT Austin) • Sujay Sanghavi (UT-Austin)

A Model to Search for Synthesizable Molecules

John Bradshaw (University of Cambridge/MPI Tuebingen) • Brooks Paige (Alan Turing Institute) • Matt J Kusner (University College London) • Marwin Segler (BenevolentAI) • José Miguel Hernández-Lobato (University of Cambridge)

Post training 4-bit quantization of convolutional networks for rapid-deployment

Ron Banner (Intel - Artificial Intelligence Products Group (AIPG)) • Yury Nahshan (Intel corp.) • Daniel Soudry (Technion)

Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes

James Requeima (University of Cambridge / Invenia Labs) • Jonathan Gordon (University of Cambridge) • John Bronskill (University of Cambridge) • Sebastian Nowozin (Microsoft Research) • Richard Turner (Cambridge)

Differentially Private Anonymized Histograms

Ananda Theertha Suresh (Google)

Dynamic Local Regret for Non-convex Online Forecasting

Sergul Aydore (Stevens Institute of Technology) • Tianhao Zhu (Stevens Institute of Techonlogy) • Dean Foster (Amazon)

Learning Local Search Heuristics for Boolean Satisfiability

Emre Yolcu (Carnegie Mellon University) • Barnabas Poczos (Carnegie Mellon University)

Provably Efficient Q-Learning with Low Switching Cost

Yu Bai (Stanford University) • Tengyang Xie (University of Illinois at Urbana-Champaign) • Nan Jiang (University of Illinois at Urbana-Champaign) • Yu-Xiang Wang (UC Santa Barbara)

Solving graph compression via optimal transport

Vikas Garg (MIT) • Tommi Jaakkola (MIT)

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Benoit Steiner (Facebook AI Research) • Zachary DeVito (Facebook AI Research) • Soumith Chintala (Facebook AI Research) • Sam Gross (Facebook) • Adam Paszke (University of Warsaw) • Francisco Massa (Facebook AI Research) • Adam Lerer (Facebook AI Research) • Gregory Chanan (Facebook) • Zeming Lin (Facebook AI Research) • Edward Yang (Facebook) • Alban Desmaison (Oxford University) • Alykhan Tejani (Twitter, Inc.) • Andreas Kopf (Xamla) • James Bradbury (Google Brain) • Luca Antiga (Orobix) • Martin Raison (Nabla) • Natalia Gimelshein (NVIDIA) • Sasank Chilamkurthy (Qure.ai) • Trevor Killeen (Self Employed) • Lu Fang (Facebook) • Junjie Bai (Facebook)

Stability of Graph Scattering Transforms

Fernando Gama (University of Pennsylvania) • Alejandro Ribeiro (University of Pennsylvania) • Joan Bruna (NYU)

A Debiased MDI Feature Importance Measure for Random Forests

Xiao Li (University of California, Berkeley) • Yu Wang (UC Berkeley) • Sumanta Basu (Cornell University) • Karl Kumbier (University of California, Berkeley) • Bin Yu (UC Berkeley)

Difference Maximization Q-learning: Provably Efficient Q-learning with Function Approximation

Simon Du (Carnegie Mellon University) • Yuping Luo (Princeton University) • Ruosong Wang (Carnegie Mellon University) • Hanrui Zhang (Duke University)

Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models

Shanshan Wu (University of Texas at Austin) • Sujay Sanghavi (UT-Austin) • Alexandros Dimakis (University of Texas, Austin)

Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks

Guodong Zhang (University of Toronto) • James Martens (DeepMind) • Roger Grosse (University of Toronto)

Rapid Convergence of the Unadjusted Langevin Algorithm: Log-Sobolev Suffices

Santosh Vempala (Georgia Tech) • Andre Wibisono ()

Learning Distributions Generated by One-Layer ReLU Networks

Shanshan Wu (University of Texas at Austin) • Alexandros Dimakis (University of Texas, Austin) • Sujay Sanghavi (UT-Austin)

Large-scale optimal transport map estimation using projection pursuit

Cheng Meng (University of Georgia) • Yuan Ke (University of Georgia) • Jingyi Zhang (The University of Georgia) • Mengrui Zhang (University of Georgia) • Wenxuan Zhong () • Ping Ma (University of Georgia)

A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning

Nicolas Carion (Facebook AI Research Paris) • Nicolas Usunier (Facebook AI Research) • Gabriel Synnaeve (Facebook) • Alessandro Lazaric (Facebook Artificial Intelligence Research)

On Exact Computation with an Infinitely Wide Neural Net

Sanjeev Arora (Princeton University) • Simon Du (Carnegie Mellon University) • Wei Hu (Princeton University) • zhiyuan li (Princeton University) • Ruslan Salakhutdinov (Carnegie Mellon University) • Ruosong Wang (Carnegie Mellon University)

Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning

Gregory Farquhar (University of Oxford) • Shimon Whiteson (University of Oxford) • Jakob Foerster (University of Oxford)

Chirality Nets for Human Pose Regression

Raymond Yeh (University of Illinois at Urbana–Champaign) • Yuan-Ting Hu (University of Illinois Urbana-Champaign) • Alexander Schwing (University of Illinois at Urbana-Champaign)

Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds

Minshuo Chen (Georgia Tech) • Haoming Jiang (Georgia Institute of Technology) • Wenjing Liao (Georgia Tech) • Tuo Zhao (Georgia Tech)

Fast Decomposable Submodular Function Minimization using Constrained Total Variation

Senanayak Sesh Kumar Karri (Imperial College, London) • Francis Bach (INRIA - Ecole Normale Superieure) • Thomas Pock (Graz University of Technology)

Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model

Guodong Zhang (University of Toronto) • Lala Li (Google) • Zachary Nado (Google Inc.) • James Martens (DeepMind) • Sushant Sachdeva (University of Toronto) • George Dahl (Google Brain) • Chris Shallue (Google Brain) • Roger Grosse (University of Toronto)

Spherical Text Embedding

Yu Meng (University of Illinois at Urbana-Champaign) • Jiaxin Huang (University of Illinois Urbana-Champaign) • Guangyuan Wang (UIUC) • Chao Zhang (Georgia Institute of Technology) • Honglei Zhuang (Google Research) • Lance Kaplan (U.S. Army Research Laboratory) • Jiawei Han (UIUC)

Möbius Transformation for Fast Inner Product Search on Graph

Zhixin Zhou (Baidu Research) • Shulong Tan (Baidu Research) • Zhaozhuo Xu (Baidu Research) • Ping Li (Baidu Research USA)

Hyperbolic Graph Neural Networks

Qi Liu (National University of Singapore) • Maximilian Nickel (Facebook AI Research) • Douwe Kiela (Facebook AI Research)

Average Individual Fairness: Algorithms, Generalization and Experiments

Saeed Sharifi-Malvajerdi (University of Pennsylvania) • Michael Kearns (University of Pennsylvania) • Aaron Roth (University of Pennsylvania)

Fixing the train-test resolution discrepancy

Hugo Touvron (Facebook AI Research) • Andrea Vedaldi (Facebook AI Research and University of Oxford) • Matthijs Douze (Facebook AI Research) • Herve Jegou (Facebook AI Research)

Modeling Dynamic Functional Connectivity with Latent Factor Gaussian Processes

Lingge Li (UC Irvine) • Dustin Pluta (UC Irvine) • Babak Shahbaba (UCI) • Norbert Fortin (UC Irvine) • Hernando Ombao (KAUST) • Pierre Baldi (UC Irvine)

Manipulating a Learning Defender and Ways to Counteract

Jiarui Gan (University of Oxford) • Qingyu Guo (Nanyang Technological University) • Long Tran-Thanh (University of Southampton) • Bo An (Nanyang Technological University) • Michael Wooldridge (Univ of Oxford)

Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations

Andrew Spielberg (Massachusetts Institute of Technology) • Allan Zhao (Massachusetts Institute of Technology) • Yuanming Hu (Massachusetts Institute of Technology) • Tao Du (MIT) • Wojciech Matusik (MIT) • Daniela Rus (Massachusetts Institute of Technology)

Learning to Infer Implicit Surfaces without 3D Supervision

Shichen Liu (Tsinghua University) • Shunsuke Saito (University of Southern California) • Weikai Chen (USC Institute for Creative Technology) • Hao Li (Pinscreen/University of Southern California/USC ICT)

Fast and Accurate Least-Mean-Squares Solvers

Ibrahim Jubran (The University of Haifa) • Alaa Maalouf (The University of Haifa) • Dan Feldman (University of Haifa)

Certifiable Robustness to Graph Perturbations

Aleksandar Bojchevski (Technical University of Munich) • Stephan Günnemann (Technical University of Munich)

Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay

Frederic Koehler (MIT)

Paradoxes in Fair Machine Learning

Paul Goelz (Carnegie Mellon University) • Anson Kahng (Carnegie Mellon University) • Ariel D Procaccia (Carnegie Mellon University)

Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost

Zhuoran Yang (Princeton University) • Yongxin Chen (Georgia Institute of Technology) • Mingyi Hong (University of Minnesota) • Zhaoran Wang (Northwestern University)

The spiked matrix model with generative priors

Benjamin Aubin (Ipht Saclay) • Bruno Loureiro (IPhT Saclay) • Antoine Maillard (Ecole Normale Supérieure) • Florent Krzakala (ENS Paris & Sorbonnes Université) • Lenka Zdeborová (CEA Saclay)

Gradient Dynamics of Shallow Low-Dimensional ReLU Networks

Francis Williams (New York University) • Matthew Trager (NYU) • Daniele Panozzo (NYU) • Claudio Silva (New York University) • Denis Zorin (New York University) • Joan Bruna (NYU)

Robust and Communication-Efficient Collaborative Learning

Amirhossein Reisizadeh (UC Santa Barbara) • Hossein Taheri (UCSB) • Aryan Mokhtari (UT Austin) • Hamed Hassani (UPenn) • Ramtin Pedarsani (UC Santa Barbara)

Multiclass Learning from Contradictions

Sauptik Dhar (LG Electronics) • Vladimir Cherkassky (University of Minnesota) • Mohak Shah (LG Electronics)

Learning from Trajectories via Subgoal Discovery

Sujoy Paul (UC Riverside) • Jeroen Vanbaar (Mitsubishi Electric Research Laboratories) • Amit Roy-Chowdhury (University of California, Riverside, USA )

Distributed Low-rank Matrix Factorization With Exact Consensus

Zhihui Zhu (Johns Hopkins University) • Qiuwei Li (Colorado School of Mines) • Xinshuo Yang (Colorado School of Mines) • Gongguo Tang (Colorado School of Mines) • Michael B Wakin (Colorado School of Mines)

Online Normalization for Training Neural Networks

Vitaliy Chiley (Cerebras Systems) • Ilya Sharapov (Cerebras Systems) • Atli Kosson (Cerebras Systems) • Urs Koster (Cerebras Systems) • Ryan Reece (Cerebras Systems) • Sofia Samaniego de la Fuente (Cerebras Systems) • Vishal Subbiah (Cerebras Systems) • Michael James (Cerebras)

The Synthesis of XNOR Recurrent Neural Networks with Stochastic Logic

Arash Ardakani (McGill University) • Zhengyun Ji (McGill University) • Amir Ardakani (McGill University) • Warren Gross (McGill University)

An adaptive Mirror-Prox method for variational inequalities with singular operators

Kimon Antonakopoulos (Inria) • Veronica Belmega (ENSEA) • Panayotis Mertikopoulos (CNRS (French National Center for Scientific Research))

N-Gram Graph: A Simple Unsupervised Representation for Molecules

Shengchao Liu (UW-Madison) • Mehmet F Demirel (University of Wisconsin-Madison) • Yingyu Liang (University of Wisconsin Madison)

Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory

Bin Hu (University of Illinois at Urbana-Champaign) • Usman A Syed (University of Illinois Urbana Champaign)

Facility Location Problem in Differential Privacy Model Revisited

Yunus Esencayi (State University of New York at Buffalo) • Marco Gaboardi (Univeristy at Buffalo) • Shi Li (University at Buffalo) • Di Wang (State University of New York at Buffalo)

Revisiting Auxiliary Latent Variables in Generative Models

John Lawson (New York University) • George Tucker (Google Brain) • Bo Dai (Google Brain) • Rajesh Ranganath (New York University)

Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator

Karl Krauth (UC berkeley) • Stephen Tu (UC Berkeley) • Benjamin Recht (UC Berkeley)

A Universally Optimal Multistage Accelerated Stochastic Gradient Method

Necdet Serhat Aybat (Penn State University) • Alireza Fallah (MIT) • Mert Gurbuzbalaban (Rutgers) • Asuman Ozdaglar (Massachusetts Institute of Technology)

From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction

Hidenori Tanaka (Stanford) • Aran Nayebi (Stanford University) • Stephen Baccus (Stanford University) • Surya Ganguli (Stanford)

Large Memory Layers with Product Keys

Guillaume Lample (Facebook AI Research) • Alexandre Sablayrolles (Facebook AI Research) • Marc'Aurelio Ranzato (Facebook AI Research) • Ludovic Denoyer (Facebook - FAIR) • Herve Jegou (Facebook AI Research)

Learning Deterministic Weighted Automata with Queries and Counterexamples

Gail Weiss (Technion) • Yoav Goldberg (Bar Ilan University) • Eran Yahav (Technion)

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

Jaehoon Lee (Google Brain) • Lechao Xiao (Google Brain) • Samuel Schoenholz (Google Brain) • Yasaman Bahri (Google Brain) • Roman Novak (Google Brain) • Jascha Sohl-Dickstein (Google Brain) • Jeffrey Pennington (Google Brain)

Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals

Surbhi Goel (UT Austin) • Sushrut Karmalkar (The University of Texas at Austin) • Adam Klivans (UT Austin)

Visualizing and Measuring the Geometry of BERT

Emily Reif (Google) • Ann Yuan (Google) • Martin Wattenberg (Google) • Fernanda B Viegas (Google) • Andy Coenen (Google) • Adam Pearce (Google) • Been Kim (Google)

Self-Critical Reasoning for Robust Visual Question Answering

Jialin Wu (UT Austin) • Raymond Mooney (University of Texas at Austin)

Learning to Screen

Alon Cohen (Technion and Google Inc.) • Avinatan Hassidim (Google) • Haim Kaplan (TAU, GOOGLE) • Yishay Mansour (Tel Aviv University / Google) • Shay Moran (IAS, Princeton)

A Communication Efficient Stochastic Multi-Block Alternating Direction Method of Multipliers

Hao Yu (Alibaba Group (US) Inc )

A Little Is Enough: Circumventing Defenses For Distributed Learning

Gilad Baruch (Bar Ilan University) • Moran Baruch (Bar Ilan University) • Yoav Goldberg (Bar-Ilan University)

Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural Networks

Gunjan Verma (ARL) • Ananthram Swami (Army Research Laboratory, Adelphi)

A Robust Non-Clairvoyant Dynamic Mechanism for Contextual Auctions

Yuan Deng (Duke University) • Sebastien Lahaie (Google Research) • Vahab Mirrokni (Google Research NYC)

Finite-Sample Analysis for SARSA with Linear Function Approximation

Shaofeng Zou (University at Buffalo, the State University of New York) • Tengyu Xu (The Ohio State University) • Yingbin Liang (The Ohio State University)

Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models

Stefano Sarao Mannelli (Institut de Physique Théorique) • Giulio Biroli (ENS) • Chiara Cammarota (King's College London) • Florent Krzakala (École Normale Supérieure) • Lenka Zdeborová (CEA Saclay)

Graph Structured Prediction Energy Networks

Colin Graber (University of Illinois at Urbana-Champaign) • Alexander Schwing (University of Illinois at Urbana-Champaign)

Private Learning Implies Online Learning: An Efficient Reduction

Alon Gonen (Princeton University) • Elad Hazan (Princeton University) • Shay Moran (IAS, Princeton)

Graph Agreement Models for Semi-Supervised Learning

Otilia Stretcu (Carnegie Mellon University) • Krishnamurthy Viswanathan (Google Research) • Dana Movshovitz-Attias (Google) • Emmanouil Platanios (Carnegie Mellon University) • Sujith Ravi (Google Research) • Andrew Tomkins (Google)

Latent distance estimation for random geometric graphs

Ernesto J Araya Valdivia (Université Paris-Sud) • Yohann De Castro (ENPC)

Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network

Jennifer Cardona (Stanford University) • Michael Howland (Stanford University) • John Dabiri (Stanford University)

The Functional Neural Process

Christos Louizos (University of Amsterdam) • Xiahan Shi (Bosch Center for Artificial Intelligence) • Klamer Schutte (TNO) • Max Welling (University of Amsterdam / Qualcomm AI Research)

Recurrent Registration Neural Networks for Deformable Image Registration

Robin Sandkühler (Department of Biomedical Engineering, University of Basel) • Simon Andermatt (Center for medical Image Analysis and Navigation) • Grzegorz Bauman (University of Basel Hospital) • Sylvia Nyilas (Bern University Hospital) • Christoph Jud (University of Basel) • Philippe C. Cattin (University of Basel)

Unsupervised State Representation Learning in Atari

Ankesh Anand (Mila, Université de Montréal) • Evan Racah (Mila, Université de Montréal) • Sherjil Ozair (Université de Montréal) • Yoshua Bengio (Mila) • Marc-Alexandre Côté (Microsoft Research) • R Devon Hjelm (Microsoft Research)

Unlocking Fairness: a Trade-off Revisited

Michael Wick (Oracle Labs) • swetasudha panda (Oracle Labs) • Jean-Baptiste Tristan (Oracle Labs)

Fisher Efficient Inference of Intractable Models

Song Liu (University of Bristol) • Takafumi Kanamori (Tokyo Institute of Technology/RIKEN) • Wittawat Jitkrittum (Max Planck Institute for Intelligent Systems) • Yu Chen (University of Bristol)

Thompson Sampling and Approximate Inference

Kieu-My Phan (University of Massachusetts Amherst) • Yasin Abbasi (Adobe Research) • Justin Domke (University of Massachusetts, Amherst)

PRNet: Self-Supervised Learning for Partial-to-Partial Registration

Yue Wang (MIT) • Justin M Solomon (MIT)

Surrogate Objectives for Batch Policy Optimization in One-step Decision Making

Minmin Chen (Google) • Ramki Gummadi (Google) • Chris Harris (Google) • Dale Schuurmans (University of Alberta & Google Brain)

Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians

Axel Brando (BBVA Data & Analytics and Universitat de Barcelona) • Jose A Rodriguez (BBVA Data & Analytics) • Jordi Vitria (Universitat de Barcelona) • Alberto Rubio Muñoz (BBVA Data & Analytics)

Learning Macroscopic Brain Connectomes via Group-Sparse Factorization

Farzane Aminmansour (University of Alberta) • Andrew Patterson (University of Alberta) • Lei Le (Indiana University Bloomington) • Yisu Peng (Northeastern University) • Daniel Mitchell (University of Alberta) • Franco Pestilli (Indiana University) • Cesar Caiafa (CONICET/RIKEN AIP) • Russell Greiner (University of Alberta) • Martha White (University of Alberta)

Approximating the Permanent by Sampling from Adaptive Partitions

Jonathan Kuck (Stanford) • Tri Dao (Stanford University) • Hamid Rezatofighi (University of Adelaide) • Ashish Sabharwal (Allen Institute for AI) • Stefano Ermon (Stanford)

Retrosynthesis Prediction with Conditional Graph Logic Network

Hanjun Dai (Georgia Tech) • Chengtao Li (MIT) • Connor Coley (MIT) • Bo Dai (Google Brain) • Le Song (Ant Financial & Georgia Institute of Technology)

Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration

Robert Kleinberg (Cornell University) • Kevin Leyton-Brown (University of British Columbia) • Brendan Lucier (Microsoft Research) • Devon Graham (University of British Columbia)

Online Learning via the Differential Privacy Lens

Jacob Abernethy (Georgia Institute of Technolog) • Young Hun Jung (Universith of Michigan) • Chansoo Lee (University of Michigan) • Audra McMillan (Boston Univ) • Ambuj Tewari (University of Michigan)

3D Object Detection from a Single RGB Image via Perspective Points

Siyuan Huang (University of California, Los Angeles) • Yixin Chen (UCLA) • Tao Yuan (UCLA) • Siyuan Qi (UCLA) • Yixin Zhu (University of California, Los Angeles) • Song-Chun Zhu (UCLA)

Parameter elimination in particle Gibbs sampling

Anna Wigren (Uppsala University) • Riccardo Sven Risuleo (Uppsala University) • Lawrence Murray (Uber AI Labs) • Fredrik Lindsten (Linköping Universituy)

This Looks Like That: Deep Learning for Interpretable Image Recognition

Chaofan Chen (Duke University) • Oscar Li (Duke University) • Chaofan Tao (Duke University) • Alina Barnett (Duke University) • Cynthia Rudin (Duke)

Adaptively Aligned Image Captioning via Adaptive Attention Time

Lun Huang (Peking University) • Wenmin Wang (Peking University) • Yaxian Xia (Peking University) • Jie Chen (Peng Cheng Laboratory)

Accurate Uncertainty Estimation and Decomposition in Ensemble Learning

Jeremiah Liu (Harvard University) • John Paisley (Columbia University) • Marianthi-Anna Kioumourtzoglou (Columbia University) • Brent Coull (Harvard University)

Learning Bayesian Networks with Low Rank Conditional Probability Tables

Adarsh Barik (Purdue University) • Jean Honorio (Purdue University)

Equal Opportunity in Online Classification with Partial Feedback

Yahav Bechavod (Hebrew University of Jerusalem) • Katrina Ligett (Hebrew University) • Aaron Roth (University of Pennsylvania) • Bo Waggoner (U. Colorado, Boulder) • Steven Wu (Microsoft Research)

Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations

Kevin Smith (MIT) • Lingjie Mei (MIT) • Shunyu Yao (Princeton University) • Jiajun Wu (MIT) • Elizabeth Spelke (Harvard University) • Josh Tenenbaum (MIT) • Tomer Ullman (MIT)

Neural Multisensory Scene Inference

Jae Hyun Lim (MILA, University of Montreal) • Pedro O. Pinheiro (Element AI) • Negar Rostamzadeh (Elemenet AI) • Chris Pal (MILA, Polytechnique Montréal, Element AI) • Sungjin Ahn (Rutgers University)

Regret Bounds for Thompson Sampling in Restless Bandit Problems

Young Hun Jung (Universith of Michigan) • Ambuj Tewari (University of Michigan)

What Can ResNet Learn Efficiently, Going Beyond Kernels?

Zeyuan Allen-Zhu (Microsoft Research) • Yuanzhi Li (Princeton)

Better Transfer Learning Through Inferred Successor Maps

Tamas Madarasz (University of Oxford) • Tim Behrens (University of Oxford)

Unsupervised Co-Learning on GG-Manifolds Across Irreducible Representations

Yifeng Fan (University of Illinois at Urbana-Champaign) • Tingran Gao (University of Chicago) • Jane Zhao (University of Illinois at Urbana Champaign)

Defending Against Neural Fake News

Rowan Zellers (University of Washington) • Ari Holtzman (University of Washington) • Hannah Rashkin (University of Washington) • Yonatan Bisk (University of Washington) • Ali Farhadi (University of Washington, Allen Institute for Artificial Intelligence) • Franziska Roesner (University of Washington) • Yejin Choi (University of Washington)

Sample Adaptive MCMC

Michael Zhu (Stanford University)

A Stochastic Composite Gradient Method with Incremental Variance Reduction

Junyu Zhang (University of Minnesota) • Lin Xiao (Microsoft Research)

Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses

Ananya Uppal (Carnegie Mellon University) • Shashank Singh (Carnegie Mellon University) • Barnabas Poczos (Carnegie Mellon University)

STAR-Caps: Capsule Networks with Straight-Through Attentive Routing

Karim Ahmed (Dartmouth) • Lorenzo Torresani (Facebook)

Limitations of Lazy Training of Two-layers Neural Network

Song Mei (Stanford University) • Theodor Misiakiewicz (Stanford University) • Behrooz Ghorbani (Stanford University) • Andrea Montanari (Stanford)

Reconciling meta-learning and continual learning with online mixtures of tasks

Ghassen Jerfel (Duke University) • Erin Grant (UC Berkeley) • Thomas Griffiths (Princeton University) • Katherine Heller (Google)

Distributionally Robust Optimization and Generalization in Kernel Methods

Matthew Staib (MIT) • Stefanie Jegelka (MIT)

A General Theory of Equivariant CNNs on Homogeneous Spaces

Taco Cohen (University of Amsterdam) • Mario Geiger (EPFL) • Maurice Weiler (University of Amsterdam)

Trivializations for Gradient-Based Optimization on Manifolds

Mario Lezcano Casado (Univeristy of Oxford)

Write, Execute, Assess: Program Synthesis with a REPL

Kevin Ellis (MIT) • Maxwell Nye (MIT) • Yewen Pu (MIT) • Felix Sosa (Harvard) • Josh Tenenbaum (MIT) • Armando Solar-Lezama (MIT)

(Nearly) Efficient Algorithms for the Graph Matching Problem on Correlated Random Graphs

Boaz Barak (Harvard University) • Chi-Ning Chou (Harvard University) • Zhixian Lei (Harvard University) • Tselil Schramm (Harvard University) • Yueqi Sheng (Harvard University )

Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models

Farnam Mansouri (Max Planck Institute for Software Systems) • Yuxin Chen (Caltech) • Ara Vartanian (University of Wisconsin -- Madison) • Jerry Zhu (University of Wisconsin-Madison) • Adish Singla (MPI-SWS)

Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback

Mingrui Zhang (Yale University) • Lin Chen (Yale University) • Hamed Hassani (UPenn) • Amin Karbasi (Yale)

Sampling Networks and Aggregate Simulation for Online POMDP Planning

Hao Cui (Tufts University) • Roni Khardon (Indiana University, Bloomington)

Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks

Gabriele Farina (Carnegie Mellon University) • Chun Kai Ling (Carnegie Mellon University) • Fei Fang (Carnegie Mellon University) • Tuomas Sandholm (Carnegie Mellon University)

GNNExplainer: Generating Explanations for Graph Neural Networks

Zhitao Ying (Stanford University) • Dylan Bourgeois (EPFL) • Jiaxuan You (Stanford University) • Marinka Zitnik (Stanford University) • Jure Leskovec (Stanford University and Pinterest)

Linear Stochastic Bandits Under Safety Constraints

Sanae Amani (University of California Santa Barbara) • Mahnoosh Alizadeh (University of California Santa Barbara) • Christos Thrampoulidis (UCSB)

A coupled autoencoder approach for multi-modal analysis of cell types

Rohan Gala (Allen Institute) • Nathan Gouwens (Allen Institute) • Zizhen Yao (Allen Institute) • Agata Budzillo (Allen Institute) • Osnat Penn (Allen Institute) • Bosiljka Tasic (Allen Institute) • Gabe Murphy (Allen Institute) • Hongkui Zeng (Allen Institute) • Uygar Sumbul (Allen Institute)

Towards Automatic Concept-based Explanations

Amirata Ghorbani (Stanford University) • James Wexler () • James Zou (Stanford University) • Been Kim (Google)

A Deep Probabilistic Model for Compressing Low Resolution Videos

Salvator Lombardo (Disney Research) • JUN HAN (Dartmouth College) • Christopher Schroers (Disney Research) • Stephan Mandt (Disney Research)

Budgeted Reinforcement Learning in Continuous State Space

Nicolas Carrara (inria) • Edouard Leurent (INRIA) • Romain Laroche (Microsoft Research) • Tanguy Urvoy (Orange-Labs) • Odalric-Ambrym Maillard (INRIA) • Olivier Pietquin (Google Research Brain Team)

The Discovery of Useful Questions as Auxiliary Tasks

Vivek Veeriah (University of Michigan) • Richard L Lewis (University of Michigan) • Janarthanan Rajendran (University of Michigan) • David Silver (DeepMind) • Satinder Singh (University of Michigan)

Sinkhorn Barycenters with Free Support via Frank-Wolfe Algorithm

Giulia Luise (University College London) • Saverio Salzo (Istituto Italiano di Tecnologia) • Massimiliano Pontil (IIT & UCL) • Carlo Ciliberto (Imperial College London)

Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias

Stéphane d'Ascoli (ENS) • Levent Sagun (EPFL) • Giulio Biroli (ENS) • Joan Bruna (NYU)

Correlation clustering with local objectives

Sanchit Kalhan (Northwestern University) • Konstantin Makarychev (Northwestern University) • Timothy Zhou (Northwestern University)

Multiclass Performance Metric Elicitation

Gaurush Hiranandani (UNIVERSITY OF ILLINOIS, URBANA-CH) • Shant Boodaghians (UIUC) • Ruta Mehta (UIUC) • Oluwasanmi Koyejo (UIUC)

Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing

Zhiqi Bu (University of Pennsylvania) • Jason Klusowski (Rutgers University) • Cynthia Rush (Columbia University) • Weijie Su (University of Pennsylvania)

Explicit Explore-Exploit Algorithms in Continuous State Spaces

Mikael Henaff (NYU)

ADDIS: an adaptive discarding algorithm for online FDR control with conservative nulls

Jinjin Tian (Carnegie Mellon University) • Aaditya Ramdas (Carnegie Mellon University)

Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

Vincent Chen (Stanford University) • Sen Wu (Stanford University) • Alexander Ratner (Stanford) • Jen Weng (Stanford University) • Christopher Ré (Stanford)

Understanding Posterior Collapse in Variational Autoencoders

James Lucas (University of Toronto) • George Tucker (Google Brain) • Roger Grosse (University of Toronto) • Mohammad Norouzi (Google Brain)

Language as an Abstraction for Hierarchical Deep Reinforcement Learning

YiDing Jiang (Google) • Shixiang (Shane) Gu (Google Brain) • Kevin P Murphy (Google) • Chelsea Finn (Google Brain)

Efficient online learning with kernels for adversarial large scale problems

Rémi Jézéquel (INRIA - Paris) • Pierre Gaillard () • Alessandro Rudi (INRIA, Ecole Normale Superieure)

A Linearly Convergent Method for Non-Smooth Non-Convex Optimization on the Grassmannian with Applications to Robust Subspace and Dictionary Learning

Zhihui Zhu (Johns Hopkins University) • Tianyu Ding (Johns Hopkins University) • Daniel Robinson (Johns Hopkins University) • Manolis Tsakiris (ShanghaiTech University) • Rene Vidal (Johns Hopkins University)

ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models

Andrei Barbu (MIT) • David Mayo (MIT) • Julian Alverio (MIT) • William Luo (MIT) • Christopher Wang (Massachusetts Institute of Technology) • Dan Gutfreund (IBM Research) • Josh Tenenbaum (MIT) • Boris Katz (MIT)

Certified Adversarial Robustness with Addition Gaussian Noise

Bai Li (Duke University) • Changyou Chen (University at Buffalo) • Wenlin Wang (Duke Univeristy) • Lawrence Carin (Duke University)

Tight Dimensionality Reduction for Sketching Low Degree Polynomial Kernels

Michela Meister (Google) • Tamas Sarlos (Google Research) • David Woodruff (Carnegie Mellon University)

Non-Cooperative Inverse Reinforcement Learning

Xiangyuan Zhang (University of Illinois at Urbana-Champaign) • Kaiqing Zhang (University of Illinois at Urbana-Champaign (UIUC)) • Erik Miehling (University of Illinois at Urbana-Champaign) • Tamer Basar ()

DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization

Rixon Crane (The University of Queensland) • Farbod Roosta-Khorasani (University of Queensland)

Sobolev Independence Criterion

Youssef Mroueh (IBM T.J Watson Research Center) • Tom Sercu (IBM Research AI) • Mattia Rigotti (IBM Research AI) • Inkit Padhi (IBM Research) • Cicero Nogueira dos Santos (IBM Research)

Maximum Entropy Monte-Carlo Planning

Chenjun Xiao (University of Alberta) • Ruitong Huang (Borealis AI) • Jincheng Mei (University of Alberta) • Dale Schuurmans (Google) • Martin Müller (University of Alberta)

Learning from brains how to regularize machines

Zhe Li (Baylor College of Medicine) • Wieland Brendel (AG Bethge, University of Tübingen) • Edgar Walker (Baylor College of Medicine) • Erick Cobos (Baylor College of Medicine) • Taliah Muhammad (Baylor College of Medicine) • Jacob Reimer (Baylor College of Medicine) • Matthias Bethge (University of Tübingen) • Fabian Sinz (University Tübingen) • Zachary Pitkow (BCM/Rice) • Andreas Tolias (Baylor College of Medicine)

Using Statistics to Automate Stochastic Optimization

Hunter Lang (Microsoft Research) • Lin Xiao (Microsoft Research) • Pengchuan Zhang (Microsoft Research)

Zero-shot Knowledge Transfer via Adversarial Belief Matching

Paul Micaelli (The University of Edinburgh) • Amos Storkey (University of Edinburgh)

Differentiable Convex Optimization Layers

Akshay Agrawal (Stanford University) • Brandon Amos (Facebook) • Shane Barratt (Stanford University) • Stephen Boyd (Stanford University) • Steven Diamond (Stanford University) • J. Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

Random Tessellation Forests

Shufei Ge (Simon Fraser University) • Shijia Wang (Simon Fraser University) • Yee Whye Teh (University of Oxford, DeepMind) • Liangliang Wang (Simon Fraser University) • Lloyd T Elliott (Simon Fraser University)

Learning Nearest Neighbor Graphs from Noisy Distance Samples

Blake Mason (University of Wisconsin - Madison) • Ardhendu Tripathy (University of Wisconsin - Madison) • Robert Nowak (University of Wisconsion-Madison)

Lookahead Optimizer: k steps forward, 1 step back

Michael Zhang (University of Toronto) • James Lucas (University of Toronto) • Jimmy Ba (University of Toronto / Vector Institute) • Geoffrey Hinton (Google)

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer

Wenzheng Chen (University of Toronto) • Huan Ling (University of Toronto, NVIDIA) • Jun Gao (University of Toronto) • Edward Smith (McGill University) • Jaakko Lehtinen (NVIDIA Research; Aalto University) • Alec Jacobson (University of Toronto) • Sanja Fidler (University of Toronto)

Covariate-Powered Empirical Bayes Estimation

Nikolaos Ignatiadis (Stanford University) • Stefan Wager (Stanford University)

Understanding the Role of Momentum in Stochastic Gradient Methods

Igor Gitman (Microsoft Research AI) • Hunter Lang (Microsoft Research) • Pengchuan Zhang (Microsoft Research) • Lin Xiao (Microsoft Research)

A neurally plausible model for online recognition andpostdiction in a dynamical environment

Li Wenliang (Gatsby Unit, UCL) • Maneesh Sahani (Gatsby Unit, UCL)

Guided Meta-Policy Search

Russell Mendonca (UC Berkeley) • Abhishek Gupta (University of California, Berkeley) • Rosen Kralev (UC Berkeley) • Pieter Abbeel (UC Berkeley Covariant) • Sergey Levine (UC Berkeley) • Chelsea Finn (Stanford University)

Marginalized Off-Policy Evaluation for Reinforcement Learning

Tengyang Xie (University of Illinois at Urbana-Champaign) • Yifei Ma (Amazon) • Yu-Xiang Wang (UC Santa Barbara)

Contextual Bandits with Cross-Learning

Santiago Balseiro (Columbia University) • Negin Golrezaei (University of Southern California) • Mohammad Mahdian (Google Research) • Vahab Mirrokni (Google Research NYC) • Jon Schneider (Google Research)

Evaluating Protein Transfer Learning with TAPE

Roshan Rao (UC Berkeley) • Nicholas Bhattacharya (UC Berkeley) • Neil Thomas (UC Berkeley) • Yan Duan (COVARIANT.AI) • Peter Chen (COVARIANT.AI) • John Canny (UC Berkeley) • Pieter Abbeel (UC Berkeley Covariant) • Yun Song (UC Berkeley)

A Bayesian Theory of Conformity in Collective Decision Making

Koosha Khalvati (University of Washington) • Saghar Mirbagheri (New York University) • Seongmin A. Park (Cognitive Neuroscience Center, CNRS) • Jean-Claude Dreher (cnrs) • Rajesh PN Rao (University of Washington)

Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel

Colin Wei (Stanford University) • Jason Lee (USC) • Qiang Liu (UT Austin) • Tengyu Ma (Stanford)

Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation

Colin Wei (Stanford University) • Tengyu Ma (Stanford)

A Benchmark for Interpretability Methods in Deep Neural Networks

Sara Hooker (Google AI Resident) • Dumitru Erhan (Google Brain) • Pieter-Jan Kindermans (Google Brain) • Been Kim (Google)

Memory Efficient Adaptive Optimization

Rohan Anil (Google) • Vineet Gupta (Google) • Tomer Koren (Google) • Yoram Singer (Google)

Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions

Negin Golrezaei (MIT) • Adel Javanmard (USC) • Vahab Mirrokni (Google Research NYC)

Convergence-Rate-Matching Discretization of Accelerated Optimization Flows Through Opportunistic State-Triggered Control

Miguel Vaquero (UCSD) • Jorge Cortes (UCSD)

A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning

Xuanqing Liu (University of California, Los Angeles) • Si Si (Google Research) • Jerry Zhu (University of Wisconsin-Madison) • Yang Li (Google) • Cho-Jui Hsieh (UCLA)

Systematic generalization through meta sequence-to-sequence learning

Brenden Lake (New York University)

Bayesian Joint Estimation of Multiple Graphical Models

Lingrui Gan (University of Illinois at Urbana and Champaign) • Xinming Yang (University of Illinois at Urbana-Champaign) • Naveen Narisetty (University of Illinois at Urbana-Champaign) • Feng Liang (Univ. of Illinois Urbana-Champaign Statistics)

Practical Two-Step Lookahead Bayesian Optimization

Jian Wu (Cornell University) • Peter Frazier (Cornell / Uber)

Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models

Yunfei Teng (New York University) • Wenbo Gao (Columbia University) • François Chalus (Credit Suisse & University of Cambridge) • Anna Choromanska (NYU) • Donald Goldfarb (Columbia University) • Adrian Weller (Cambridge, Alan Turing Institute)

A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks

Hadi Salman (Microsoft Research AI) • Greg Yang (Microsoft Research) • Huan Zhang (UCLA) • Cho-Jui Hsieh (UCLA) • Pengchuan Zhang (Microsoft Research)

Neural Jump Stochastic Differential Equations

Junteng Jia (Cornell) • Austin Benson (Cornell University)

Learning metrics for persistence-based summaries and applications for graph classification

Qi Zhao (The Ohio State University) • Yusu Wang (Ohio State University)

ON THE VALUE OF TARGET SAMPLING IN COVARIATE-SHIFT

Steve Hanneke (Toyota Technological Institute at Chicago) • Samory Kpotufe (Columbia University)

Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization

Adithya M Devraj (University of Florida ) • Jianshu Chen (Tencent AI Lab)

On Robustness of Principal Component Regression

Anish Agarwal (MIT) • Devavrat Shah (Massachusetts Institute of Technology) • Dennis Shen (Massachusetts Institute of Technology) • Dogyoon Song (Massachusetts Institute of Technology)

Meta Learning with Relational Information for Short Sequences

Yujia Xie (Georgia Institute of Technology) • Haoming Jiang (Georgia Institute of Technology) • Feng Liu (Florida Atlantic University) • Tuo Zhao (Georgia Tech) • Hongyuan Zha (Georgia Tech)

Residual Flows for Invertible Generative Modeling

Tian Qi Chen (U of Toronto) • Jens Behrmann (University of Bremen) • David Duvenaud (University of Toronto) • Joern-Henrik Jacobsen (Vector Institute)

Multi-Agent Common Knowledge Reinforcement Learning

Christian Schroeder (University of Oxford) • Jakob Foerster (University of Oxford) • Gregory Farquhar (University of Oxford) • Philip Torr (University of Oxford) • Wendelin Boehmer (University of Oxford) • Shimon Whiteson (University of Oxford)

Learning to Learn By Self-Critique

Antreas Antoniou (University of Edinburgh) • Amos Storkey (University of Edinburgh)

Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes

Greg Yang (Microsoft Research)

Neural Networks with Cheap Differential Operators

Tian Qi Chen (U of Toronto) • David Duvenaud (University of Toronto)

Transductive Zero-Shot Learning with Visual Structure Constraint

Ziyu Wan (City University of Hong Kong) • Dongdong Chen (university of science and technology of china) • Yan Li (Institute of Automation, Chinese Academy of Sciences) • Xingguang Yan (Shenzhen University) • Junge Zhang (CASIA) • Yizhou Yu (Deepwise AI Lab) • Jing Liao (City University of Hong Kong)

Dying Experts: Efficient Algorithms with Optimal Regret Bounds

Hamid Shayestehmanesh (University of Victoria) • Sajjad Azami (University of Victoria) • Nishant Mehta (University of Victoria)

Model similarity mitigates test set overuse

Horia Mania (UC Berkeley) • John Miller (University of California, Berkeley) • Ludwig Schmidt (UC Berkeley) • Moritz Hardt (University of California, Berkeley) • Benjamin Recht (UC Berkeley)

A unified theory for the origin of grid cells through the lens of pattern formation

Ben Sorscher (Stanford University) • Gabriel Mel (Stanford University) • Surya Ganguli (Stanford) • Samuel Ocko (Stanford)

On Sample Complexity Upper and Lower Bounds for Exact Ranking from Noisy Comparisons

Wenbo Ren (The Ohio State University) • Jia Liu (Iowa State University) • Ness Shroff (The Ohio State University)

Hierarchical Decision Making by Generating and Following Natural Language Instructions

Hengyuan Hu (Facebook) • Denis Yarats (New York University) • Qucheng Gong (Facebook AI Research) • Yuandong Tian (Facebook AI Research) • Mike Lewis (Facebook)

SHE: A Fast and Accurate Deep Neural Network for Encrypted Data

Qian Lou (Indiana University) • Lei Jiang (Indiana University Bloomington)

Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond

Lin Chen (Yale University) • Hossein Esfandiari (Google Research) • Gang Fu (Google Inc) • Vahab Mirrokni (Google Research NYC)

A Game Theoretic Approach to Class-wise Selective Rationalization

Shiyu Chang (IBM T.J. Watson Research Center) • Yang Zhang (IBM T. J. Watson Research) • Mo Yu (IBM Research) • Tommi Jaakkola (MIT)

Efficiently avoiding saddle points with zero order methods: No gradients required

Emmanouil Vlatakis-Gkaragkounis (Columbia University) • Lampros Flokas (Columbia University) • Georgios Piliouras (Singapore University of Technology and Design)

Metamers of neural networks reveal divergence from human perceptual systems

Jenelle Feather (MIT) • Alex Durango (MIT) • Ray Gonzalez (MIT) • Josh McDermott (Massachusetts Institute of Technology)

Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization

Yujiao Shi (ANU) • Liu Liu (ANU) • Xin Yu (Australian National University) • Hongdong Li (Australian National University)

Decentralized sketching of low rank matrices

Rakshith Sharma (Georgia Tech) • Kiryung Lee (Ohio state university) • Marius Junge (University of Illinois) • Justin Romberg (Georgia Institute of Technology)

Average Case Column Subset Selection for Entrywise ℓ1ℓ1-Norm Loss

Zhao Song (University of Washington) • David Woodruff (Carnegie Mellon University) • Peilin Zhong (Columbia University)

Efficient Forward Architecture Search

Hanzhang Hu (Carnegie Mellon University) • John Langford (Microsoft Research New York) • Rich Caruana (Microsoft) • Saurajit Mukherjee (microsoft) • Eric J Horvitz (Microsoft Research) • Debadeepta Dey (Microsoft Research AI)

Unsupervised Meta Learning for Few-Show Image Classification

Siavash Khodadadeh (University of Central Florida) • Ladislau Boloni (University of Central Florida) • Mubarak Shah (University of Central Florida)

Learning Mixtures of Plackett-Luce Models from Structured Partial Orders

Zhibing Zhao (RPI) • Lirong Xia (RPI)

Certainty Equivalence is Efficient for Linear Quadratic Control

Horia Mania (UC Berkeley) • Stephen Tu (UC Berkeley) • Benjamin Recht (UC Berkeley)

Scalable Bayesian inference of dendritic voltage via spatiotemporal recurrent state space models

Ruoxi Sun (Columbia University) • Ian Kinsella (Columbia University) • Scott Linderman (Columbia University) • Liam Paninski (Columbia University)

Logarithmic Regret for Online Control

Naman Agarwal (Google) • Elad Hazan (Princeton University) • Karan Singh (Princeton University)

Elliptical Perturbations for Differential Privacy

Matthew Reimherr (Penn State University) • Jordan Awan (Penn State University)

Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks

Yaqin Zhou (Nanyang Technological University) • Shangqing Liu (Nanyang Technological University) • Jingkai Siow (Nanyang Technological University) • Xiaoning Du (Nanyang Technological University) • Yang Liu (Nanyang Technology University, Singapore)

KNG: The K-Norm Gradient Mechanism

Matthew Reimherr (Penn State University) • Jordan Awan (Penn State University)

CXPlain: Causal Explanations for Model Interpretation under Uncertainty

Patrick Schwab (ETH Zurich) • Walter Karlen (ETH Zurich)

Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning

Wenjie Shi (Tsinghua University) • Shiji Song (Department of Automation, Tsinghua University) • Hui Wu (Tsinghua University) • Ya-Chu Hsu (Tsinghua University) • Cheng Wu (Tsinghua) • Gao Huang (Tsinghua)

STREETS: A Novel Camera Network Dataset for Traffic Flow

Corey Snyder (University of Illinois at Urbana-Champaign) • Minh Do (University of Illinois)

Sequential Neural Processes

Gautam Singh (Rutgers Univerity) • Jaesik Yoon (SAP) • Youngsung Son (Electronics and Telecommunications Research Institute) • Sungjin Ahn (Rutgers University)

Policy Continuation with Hindsight Inverse Dynamics

Hao Sun (CUHK) • Zhizhong Li (The Chinese University of Hong Kong) • Xiaotong Liu (Peking Uinversity) • Bolei Zhou (CUHK) • Dahua Lin (The Chinese University of Hong Kong)

Learning to Self-Train for Semi-Supervised Few-Shot Classification

Xinzhe Li (SJTU) • Qianru Sun (National University of Singapore) • Yaoyao Liu (Tianjin University) • Qin Zhou (Alibaba Group) • Shibao Zheng (SJTU) • Tat-Seng Chua (National Univ. of Singapore) • Bernt Schiele (Max Planck Institute for Informatics)

Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.

Sawyer Birnbaum (Stanford University) • Volodymyr Kuleshov (Stanford University / Afresh) • Zayd Enam (Stanford) • Pang Wei W Koh (Stanford University) • Stefano Ermon (Stanford)

From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization

Krzysztof M Choromanski (Google Brain Robotics) • Aldo Pacchiano (UC Berkeley) • Jack Parker-Holder (Columbia University) • Yunhao Tang (Columbia University) • Vikas Sindhwani (Google)

On the Expressive Power of Deep Polynomial Neural Networks

Joe Kileel (Princeton University) • Matthew Trager (NYU) • Joan Bruna (NYU)

DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation

Shashank Rajput (University of Wisconsin - Madison) • Hongyi Wang (University of Wisconsin-Madison) • Zachary Charles (University of Wisconsin - Madison) • Dimitris Papailiopoulos (University of Wisconsin-Madison)

Can SGD Learn Recurrent Neural Networks with Provable Generalization?

Zeyuan Allen-Zhu (Microsoft Research) • Yuanzhi Li (Princeton)

Limits of Private Learning with Access to Public Data

Raef Bassily (The Ohio State University) • Shay Moran (IAS, Princeton) • Noga Alon (Princeton)

Discrete Object Generation with Reversible Inductive Construction

Ari Seff (Princeton University) • Wenda Zhou (Columbia University) • Farhan Damani (Princeton University) • Abigail Doyle (Princeton University) • Ryan Adams (Princeton University)

Efficient Near-Optimal Testing of Community Changes in Balanced Stochastic Block Models

Aditya Gangrade (Boston University) • Praveen Venkatesh (Carnegie Mellon University) • Bobak Nazer (Boston University) • Venkatesh Saligrama (Boston University)

Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards

Alexander Trott (Salesforce Research) • Stephan Zheng (Salesforce) • Caiming Xiong (Salesforce) • Richard Socher (Salesforce)

Superset Technique for Approximate Recovery in One-Bit Compressed Sensing

Larkin H Flodin (University of Massachusetts Amherst) • Venkata Gandikota (University of Massachusetts, Amherst) • Arya Mazumdar (University of Massachusetts Amherst)

Bandits with Feedback Graphs and Switching Costs

Raman Arora (Johns Hopkins University) • Teodor Vanislavov Marinov (Johns Hopkins University) • Mehryar Mohri (Courant Inst. of Math. Sciences & Google Research)

Functional Adversarial Attacks

Cassidy Laidlaw (University of Maryland) • Soheil Feizi (University of Maryland, College Park)

Statistical-Computational Tradeoff in Single Index Models

Lingxiao Wang (Northwestern University) • Zhuoran Yang (Princeton University) • Zhaoran Wang (Northwestern University)

On Fenchel Mini-Max Learning

Chenyang Tao (Duke University) • Liqun Chen (Duke University) • Shuyang Dai (Duke University) • Junya Chen (Duke U) • Ke Bai (Duke University) • Dong Wang (Duke University) • Jianfeng Feng (Fudan University) • Wenlian Lu (Fudan University) • Georgiy Bobashev (RTI International) • Lawrence Carin (Duke University)

MarginGAN: Adversarial Training in Semi-Supervised Learning

Jinhao Dong (Xidian University) • Tong Lin (Peking University)

Poincar'{e} Recurrence, Cycles and Spurious Equilibria in Gradient Descent for Non-Convex Non-Concave Zero-Sum Games

Emmanouil Vlatakis-Gkaragkounis (Columbia University) • Lampros Flokas (Columbia University) • Georgios Piliouras (Singapore University of Technology and Design)

A unified variance-reduced accelerated gradient method for convex optimization

Guanghui Lan (Georgia Tech) • Zhize Li (Tsinghua University) • Yi Zhou (IBM Almaden Research Center)

Nearly Tight Bounds for Robust Proper Learning of Halfspaces with a Margin

Ilias Diakonikolas (USC) • Daniel Kane (UCSD) • Pasin Manurangsi (Google)

Same-Cluster Querying for Overlapping Clusters

Wasim Huleihel (Tel-Aviv University) • Arya Mazumdar (University of Massachusetts Amherst) • Muriel Medard (MIT) • Soumyabrata Pal (University of Massachusetts Amherst)

Efficient Convex Relaxations for Streaming PCA

Raman Arora (Johns Hopkins University) • Teodor Vanislavov Marinov (Johns Hopkins University)

Learning Robust Global Representations by Penalizing Local Predictive Power

Haohan Wang (Carnegie Mellon University) • Songwei Ge (Carnegie Mellon University) • Zachary Lipton (Carnegie Mellon University) • Eric Xing (Petuum Inc. / Carnegie Mellon University)

Unsupervised Curricula for Visual Meta-Reinforcement Learning

Allan Jabri (UC Berkeley) • Kyle Hsu (University of Toronto) • Ben Eysenbach (Carnegie Mellon University) • Abhishek Gupta (University of California, Berkeley) • Alexei Efros (UC Berkeley) • Sergey Levine (UC Berkeley) • Chelsea Finn (Stanford University)

Sample Complexity of Learning Mixture of Sparse Linear Regressions

Akshay Krishnamurthy (Microsoft) • Arya Mazumdar (University of Massachusetts Amherst) • Andrew McGregor (University of Massachusetts Amherst) • Soumyabrata Pal (University of Massachusetts Amherst)

Large Scale Adversarial Representation Learning

Jeff Donahue (DeepMind) • Karen Simonyan (DeepMind)

G2SAT: Learning to Generate SAT Formulas

Jiaxuan You (Stanford University) • Haoze Wu (Stanford University) • Clark Barrett (Stanford University) • Raghuram Ramanujan (Davidson College) • Jure Leskovec (Stanford University and Pinterest)

Neural Proximal Policy Optimization Attains Optimal Policy

Boyi Liu (Northwestern University) • Qi Cai (Northwestern University) • Zhuoran Yang (Princeton University) • Zhaoran Wang (Northwestern University)

Dimensionality reduction: theoretical perspective on practical measures

Yair Bartal (Hebrew University) • Nova Fandina (Hebrew University ) • Ofer Neiman (Ben-Gurion University)

Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback

Shinji Ito (NEC Corporation, University of Tokyo) • Daisuke Hatano (RIKEN AIP) • Hanna Sumita (Tokyo Metropolitan University) • Kei Takemura (NEC Corporation) • Takuro Fukunaga (Chuo University, JST PRESTO, RIKEN AIP) • Naonori Kakimura (Keio University) • Ken-Ichi Kawarabayashi (National Institute of Informatics)

Multilabel reductions: what is my loss optimising?

Aditya Menon (Google) • Ankit Singh Rawat (Google Research) • Sashank Reddi (Google) • Sanjiv Kumar (Google Research)

Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks

Yuan Cao (UCLA) • Quanquan Gu (UCLA)

Deep Gamblers: Learning to Abstain with Portfolio Theory

Ziyin Liu (University of Tokyo) • Zhikang Wang (University of Tokyo) • Paul Pu Liang (Carnegie Mellon University) • Ruslan Salakhutdinov (Carnegie Mellon University) • Louis-Philippe Morency (Carnegie Mellon University) • Masahito Ueda (University of Tokyo)

Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples

Tengyu Xu (The Ohio State University) • Shaofeng Zou (University at Buffalo, the State University of New York) • Yingbin Liang (The Ohio State University)

Transfer Learning via Boosting to Minimize the Performance Gap Between Domains

Boyu Wang (University of Western Ontario) • Jorge A Mendez (University of Pennsylvania) • Mingbo Cai (Princeton University) • Eric Eaton (University of Pennsylvania)

Splitting Steepest Descent for Progressive Training of Neural Networks

Lemeng Wu (UT Austin ) • Dilin Wang (UT Austin) • Qiang Liu (UT Austin)

Sequential Experimental Design for Transductive Linear Bandits

Lalit Jain (University of Washington) • Kevin Jamieson (U Washington) • Tanner Fiez (University of Washington) • Lillian Ratliff (University of Washington)

Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence

Aditya Sharad Golatkar (University of California, Los Angeles) • Alessandro Achille (UCLA) • Stefano Soatto (UCLA)

Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering

Ilias Diakonikolas (USC) • Daniel Kane (UCSD) • Sushrut Karmalkar (The University of Texas at Austin) • Eric Price (University of Texas at Austin) • Alistair Stewart (University of Southern California)

Variational Graph Recurrent Neural Networks

Ehsan Hajiramezanali (Texas A&M University) • Arman Hasanzadeh (Texas A&M University) • Krishna Narayanan (Texas A&M University) • Nick Duffield (Texas A&M University) • Mingyuan Zhou (University of Texas at Austin) • Xiaoning Qian (Texas A&M)

Semi-Implicit Graph Variational Auto-Encoders

Arman Hasanzadeh (Texas A&M University) • Ehsan Hajiramezanali (Texas A&M University) • Krishna Narayanan (Texas A&M University) • Nick Duffield (Texas A&M University) • Mingyuan Zhou (University of Texas at Austin) • Xiaoning Qian (Texas A&M)

Unsupervised Learning of Object Keypoints for Perception and Control

Tejas Kulkarni (DeepMind) • Ankush Gupta (DeepMind) • Catalin Ionescu (Deepmind) • Sebastian Borgeaud (DeepMind) • Malcolm Reynolds (DeepMind) • Andrew Zisserman (DeepMind & University of Oxford) • Volodymyr Mnih (DeepMind)

InteractiveRecGAN: a Model Based Reinforcement Learning Method with Adversarial Training for Online Recommendation

Xueying Bai (Stony Brook University) • Jian Guan (Tsinghua University) • Hongning Wang (University of Virginia)

Optimizing Generalized Rate Metrics through Three-player Games

Harikrishna Narasimhan (Google) • Andrew Cotter (Google) • Maya Gupta (Google)

Consistency-based Semi-supervised Learning for Object detection

Jisoo Jeong (Seoul National University) • Seungeui Lee (Seoul National University) • Jeesoo Kim (Seoul National University) • Nojun Kwak (Seoul National University)

Rates of Convergence for Large-scale Nearest Neighbor Classification

Xingye Qiao (Binghamton University) • Jiexin Duan (Purdue University) • Guang Cheng (Purdue University)

An Embedding Framework for Consistent Polyhedral Surrogates

Jessica Finocchiaro (University of Colorado Boulder) • Rafael Frongillo (CU Boulder) • Bo Waggoner (U. Colorado, Boulder)

Cross-Modal Learning with Adversarial Samples

CHAO LI (Xidian University) • Shangqian Gao (University of Pittsburgh) • Cheng Deng (Xidian University) • De Xie (XiDian University) • Wei Liu (Tencent AI Lab)

Fast PAC-Bayes via Shifted Rademacher Complexity

Jun Yang (University of Toronto) • Shengyang Sun (University of Toronto) • Daniel Roy (Univ of Toronto & Vector)

Cell-Attention Reduces Vanishing Saliency of Recurrent Neural Networks

Aya Abdelsalam Ismail (University of Maryland) • Mohamed Gunady (University of Maryland) • Luiz Pessoa (University of Maryland) • Hector Corrada Bravo (University of Maryland) • Soheil Feizi (University of Maryland, College Park)

Program Synthesis and Semantic Parsing with Learned Code Idioms

Richard Shin (UC Berkeley) • Miltiadis Allamanis (Microsoft Research) • Marc Brockschmidt (Microsoft Research) • Alex Polozov (Microsoft Research)

Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks

Yuan Cao (UCLA) • Quanquan Gu (UCLA)

High-Dimensional Optimization in Adaptive Random Subspaces

Jonathan Lacotte (Stanford University) • Mert Pilanci (Stanford) • Marco Pavone (Stanford University)

Random Projections with Asymmetric Quantization

Xiaoyun Li (Rutgers University) • Ping Li (Baidu Research USA)

Superposition of many models into one

Brian Cheung (UC Berkeley) • Alexander Terekhov (UC Berkeley) • Yubei Chen (UC Berkeley) • Pulkit Agrawal (UC Berkeley) • Bruno Olshausen (Redwood Center/UC Berkeley)

Private Testing of Distributions via Sample Permutations

Maryam Aliakbarpour (MIT) • Ilias Diakonikolas (USC) • Daniel Kane (UCSD) • Ronitt Rubinfeld (MIT, TAU)

McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds

Rui (Ray) Zhang (School of Mathematics, Monash University) • Xingwu Liu (University of Chinese Academy of Sciences) • Yuyi Wang (ETH Zurich) • Liwei Wang (Peking University)

How to Initialize your Network? Robust Initialization for WeightNorm & ResNets

Devansh Arpit (MILA, UdeM) • Víctor Campos (Barcelona Supercomputing Center) • Yoshua Bengio (U. Montreal)

On Making Stochastic Classifiers Deterministic

Andrew Cotter (Google) • Maya Gupta (Google) • Harikrishna Narasimhan (Google)

Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection

Xiaoyi Gu (Carnegie Mellon University) • Leman Akoglu (CMU) • Alessandro Rinaldo (CMU)

Improving Black-box Adversarial Attacks with a Transfer-based Prior

Shuyu Cheng (Tsinghua University) • Yinpeng Dong (Tsinghua University) • Tianyu Pang (Tsinghua University) • Hang Su (Tsinghua Univiersity) • Jun Zhu (Tsinghua University)

Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks

Sitao Luan (McGill University) • Mingde Zhao (Mila, McGill University) • Xiao-Wen Chang (McGill University) • Doina Precup (McGill University / DeepMind Montreal)

Statistical Model Aggregation via Parameter Matching

Mikhail Yurochkin (IBM Research, MIT-IBM Watson AI Lab) • Mayank Agarwal (IBM Research) • Soumya Ghosh (IBM Research) • Kristjan Greenewald (IBM Research) • Nghia Hoang (IBM Research)

On the (in)fidelity and sensitivity of explanations

Chih-Kuan Yeh (Carnegie Mellon University) • Cheng-Yu Hsieh (National Taiwan University) • Arun Suggala (Carnegie Mellon University) • David Inouye (Carnegie Mellon University) • Pradeep Ravikumar (Carnegie Mellon University)

Exponential Family Estimation via Adversarial Dynamics Embedding

Bo Dai (Google Brain) • Zhen Liu (Georgia Institute of Technology) • Hanjun Dai (Georgia Institute of Technology) • Niao He (UIUC) • Arthur Gretton (Gatsby Unit, UCL) • Le Song (Ant Financial & Georgia Institute of Technology) • Dale Schuurmans (Google Inc.)

The Broad Optimality of Profile Maximum Likelihood

Yi Hao (University of California, San Diego) • Alon Orlitsky (University of California, San Diego)

MintNet: Building Invertible Neural Networks with Masked Convolutions

Yang Song (Stanford University) • Chenlin Meng (Stanford University) • Stefano Ermon (Stanford)

Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates

Gintare Karolina Dziugaite (Element AI & University of Cambridge) • Mahdi Haghifam (University of Toronto) • Jeffrey Negrea (University of Toronto) • Ashish Khisti (University of Toronto) • Daniel Roy (Univ of Toronto & Vector)

On Distributed Averaging for Stochastic k-PCA

Aditya Bhaskara (Google Research) • Pruthuvi Wijewardena (University of Utah)

Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation

Ke Wang (Peking University) • Hang Hua (Peking University) • Xiaojun Wan (Peking University)

MaxGap Bandit: Adaptive Algorithms for Approximate Ranking

Sumeet Katariya (Amazon) • Ardhendu Tripathy (University of Wisconsin - Madison) • Robert Nowak (University of Wisconsion-Madison)

Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting

Aditya Grover (Stanford University) • Jiaming Song (Stanford University) • Ashish Kapoor (Microsoft Research) • Kenneth Tran (Microsoft Research) • Alekh Agarwal (Microsoft Research) • Eric J Horvitz (Microsoft Research) • Stefano Ermon (Stanford)

Online Forecasting of Total-Variation-bounded Sequences

Dheeraj Baby () • Yu-Xiang Wang (UC Santa Barbara)

Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization

Farzin Haddadpour (Pennsylvania State university) • Mohammad Mahdi Kamani (Pennsylvania State University) • Mehrdad Mahdavi (Pennsylvania State University) • Viveck Cadambe (Penn State)

Dynamic Curriculum Learning by Gradient Descent

Shreyas Saxena (Apple Inc.) • Oncel Tuzel (Apple) • Dennis DeCoste (Apple)

Unified Sample-Optimal Property Estimation in Near-Linear Time

Yi Hao (University of California, San Diego) • Alon Orlitsky (University of California, San Diego)

Region Mutual Information Loss for Semantic Segmentation

Shuai Zhao (Zhejiang University) • Yang Wang (Huazhong University of Science and Technology) • Zheng Yang (FABU) • Deng Cai (ZJU)

Learning Stable Deep Dynamics Models

J. Zico Kolter (Carnegie Mellon University / Bosch Center for AI) • Gaurav Manek (Carnegie Mellon University)

Image Captioning: Transforming Objects into Words

Simao Herdade (Yahoo Research) • Armin Kappeler (Yahoo Research) • Kofi Boakye (Yahoo Research ) • Joao Soares (Yahoo Research)

Greedy Sampling for Approximate Clustering in the Presence of Outliers

Aditya Bhaskara (Google Research) • Sharvaree Vadgama (University of Utah) • Hong Xu (University of Utah)

Adversarial Fisher Vectors for Unsupervised Representation Learning

Joshua M Susskind (Apple Inc.) • Shuangfei Zhai (Apple) • Walter Talbott (Apple) • Carlos Guestrin (Apple & University of Washington)

On Tractable Computation of Expected Predictions

Pasha Khosravi (UCLA) • YooJung Choi (UCLA) • Yitao Liang (UCLA) • Antonio Vergari (Max-Planck Institute for Intelligent Systems) • Guy Van den Broeck (UCLA)

Levenshtein Transformer

Jiatao Gu (Facebook AI Research) • Changhan Wang (Facebook AI Research) • Junbo Zhao (New York University)

Unlabeled Data Improves Adversarial Robustness

Yair Carmon (Stanford) • Aditi Raghunathan (Stanford University) • Ludwig Schmidt (UC Berkeley) • John Duchi (Stanford) • Percy Liang (Stanford University)

Machine Teaching of Active Sequential Learners

Tomi Peltola (Aalto University) • Mustafa Mert Çelikok (Aalto University) • Pedram Daee (Aalto University) • Samuel Kaski (Aalto University)

Gaussian-Based Pooling for Convolutional Neural Networks

Takumi Kobayashi (National Institute of Advanced Industrial Science and Technology)

Meta Architecture Search

Albert Shaw (Deepscale) • Wei Wei (Google AI) • Weiyang Liu (Georgia Institute of Technology) • Le Song (Ant Financial & Georgia Institute of Technology) • Bo Dai (Google Brain)

NAOMI: Non-Autoregressive Multiresolution Sequence Imputation

Yukai Liu (Caltech) • Rose Yu (Northeastern University) • Stephan Zheng (Salesforce) • Eric Zhan (Caltech) • Yisong Yue (Caltech)

Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks

Difan Zou (University of California, Los Angeles) • Ziniu Hu (UCLA) • Yewen Wang (UCLA) • Song Jiang (University of California, Los Angeles) • Yizhou Sun (UCLA) • Quanquan Gu (UCLA)

Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test

Lizhong Ding (Inception Institute of Artificial Intelligence) • Mengyang Yu (Inception Institute of Artificial Intelligence) • Li Liu (Inception Institute of Artificial Intelligence) • Fan Zhu (Inception Institute of Artificial Intelligence) • Yong Liu (Institute of Information Engineering, CAS) • Yu Li (King Abdullah University of Science and Technology) • Ling Shao (Inception Institute of Artificial Intelligence)

Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards

Anmol Kagrecha (Indian Institute of Technology Bombay) • Jayakrishnan Nair ("Assist. Prof, EE, IIT Bombay") • Krishna Jagannathan (Indian Institute of Technology Madras)

Private Stochastic Convex Optimization with Optimal Rates

Raef Bassily (The Ohio State University) • Vitaly Feldman (Google Brain) • Kunal Talwar (Google) • Abhradeep Guha Thakurta (University of California Santa Cruz)

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Hadi Salman (Microsoft Research AI) • Jerry Li (Microsoft) • Ilya Razenshteyn (Microsoft Research) • Pengchuan Zhang (Microsoft Research) • Huan Zhang (Microsoft Research AI) • Sebastien Bubeck (Microsoft Research) • Greg Yang (Microsoft Research)

Demystifying Black-box Models with Symbolic Metamodels

Ahmed Alaa (UCLA) • Mihaela van der Schaar (University of Cambridge, Alan Turing Institute and UCLA)

Neural Temporal-Difference Learning Converges to Global Optima

Qi Cai (Northwestern University) • Zhuoran Yang (Princeton University) • Jason Lee (USC) • Zhaoran Wang (Northwestern University)

Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces

Baoxiang Wang (The Chinese University of Hong Kong) • Nidhi Hegde (Borealis AI)

Attentive State-Space Modeling of Disease Progression

Ahmed Alaa (UCLA) • Mihaela van der Schaar (University of Cambridge, Alan Turing Institute and UCLA)

Online EXP3 Learning in Adversarial Bandits with Delayed Feedback

Ilai Bistritz (Stanford) • Zhengyuan Zhou (Stanford University) • Xi Chen (New York University) • Nicholas Bambos () • Jose Blanchet (Stanford University)

A Direct tilde{O}(1/epsilon) Iteration Parallel Algorithm for Optimal Transport

Arun Jambulapati (Stanford University) • Aaron Sidford (Stanford) • Kevin Tian (Stanford University)

Faster Boosting with Smaller Memory

Julaiti Alafate (University of California San Diego) • Yoav S Freund (University of California, San Diego)

Variance Reduction for Matrix Games

Yair Carmon (Stanford) • Yujia Jin (Stanford University) • Aaron Sidford (Stanford) • Kevin Tian (Stanford University)

Learning Neural Networks with Adaptive Regularization

Han Zhao (Carnegie Mellon University) • Yao-Hung Tsai (Carnegie Mellon University) • Ruslan Salakhutdinov (Carnegie Mellon University) • Geoffrey Gordon (MSR Montréal & CMU)

Distributed estimation of the inverse Hessian by determinantal averaging

Michal Derezinski (UC Berkeley) • Michael W Mahoney (UC Berkeley)

Smoothing Structured Decomposable Circuits

Andy Shih (UCLA) • Guy Van den Broeck (UCLA) • Paul Beame (University of Washington) • Antoine Amarilli (LTCI, Télécom ParisTech)

Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks

Mahyar Fazlyab (University of Pennsylvania) • Alexander Robey (University of Pennsylvania) • Hamed Hassani (UPenn) • Manfred Morari (University of Pennsylvania) • George Pappas (University of Pennsylvania)

Provable Non-linear Inductive Matrix Completion

Kai Zhong (Amazon) • Zhao Song (UT-Austin) • Prateek Jain (Microsoft Research) • Inderjit S Dhillon (UT Austin & Amazon)

Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback

Shuai Zheng (HKUST) • Ziyue Huang (Hong Kong University of Science and Technology) • James Kwok (Hong Kong University of Science and Technology)

Sparse Variational Inference: Bayesian Coresets from Scratch

Trevor Campbell (UBC) • Boyan Beronov (UBC)

Many-Armed Bandits with High-Dimensional Contexts under a Low-Rank Structure

Nima Hamidi (Stanford University) • Mohsen Bayati (Stanford University) • Kapil Gupta (Airbnb)

A Necessary and Sufficient Stability Notion for Adaptive Generalization

Moshe Shenfeld (Hebrew University of Jerusalem) • Katrina Ligett (Hebrew University)

Necessary and Sufficient Geometries for Adaptive Gradient Algorithms

Daniel Levy (Stanford University) • John Duchi (Stanford)

Landmark Ordinal Embedding

Nikhil Ghosh (Caltech) • Yuxin Chen (Caltech) • Yisong Yue (Caltech)

Identification of Conditional Causal Effects under Markov Equivalence

Amin Jaber (Purdue University) • Jiji Zhang (Lingnan University) • Elias Bareinboim (Purdue)

The Thermodynamic Variational Objective

Vaden Masrani (University of British Columbia) • Tuan Anh Le (University of Oxford) • Frank Wood (University of British Columbia)

Global Guarantees for Blind Demodulation with Generative Priors

Paul Hand (Northeastern University) • Babhru Joshi (Rice University)

Exact sampling of determinantal point processes with sublinear time preprocessing

Michal Derezinski (UC Berkeley) • Daniele Calandriello (LCSL IIT/MIT) • Michal Valko (DeepMind Paris and Inria Lille - Nord Europe)

Geometry-Aware Neural Rendering

Josh Tobin (OpenAI) • Wojciech Zaremba (OpenAI) • Pieter Abbeel (UC Berkeley Covariant)

Variational Temporal Abstraction

Taesup Kim (Mila / Kakao Brain) • Sungjin Ahn (Rutgers University) • Yoshua Bengio (U. Montreal)

Subquadratic High-Dimensional Hierarchical Clustering

Amir Abboud (IBM research) • Vincent Cohen-Addad (CNRS & Sorbonne Université) • Hussein Houdrouge (Ecole Polytechnique)

Learning Auctions with Robust Incentive Guarantees

Jacob Abernethy (Georgia Institute of Technolog) • Rachel Cummings (Georgia Tech) • Bhuvesh Kumar (Georgia Tech) • Sam Taggart (Oberlin College) • Jamie Morgenstern (Georgia Tech)

Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games

Kaiqing Zhang (University of Illinois at Urbana-Champaign (UIUC)) • Zhuoran Yang (Princeton University) • Tamer Basar ()

Uniform convergence may be unable to explain generalization in deep learning

Vaishnavh Nagarajan (Carnegie Mellon University) • J. Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

A Zero-Positive Learning Approach for Diagnosing Software Performance Regressions

Mejbah Alam (Intel Labs) • Justin Gottschlich (Intel Labs) • Nesime Tatbul (Intel Labs and MIT) • Javier Turek (Intel Labs) • Timothy Mattson (Intel) • Abdullah Muzahid (Texas A&M University)

DTWNet: a Dynamic Time Warping Network

Xingyu Cai (University of Connecticut) • Tingyang Xu (Tencent AI Lab) • Jinfeng Yi (JD Research) • Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) • Sanguthevar Rajasekaran (University of Connecticut)

Structured Graph Learning Via Laplacian Spectral Constraints

Sandeep Kumar (Hong Kong University of Science and Technology) • Jiaxi Ying (HKUST) • Jose Vinicius de Miranda Cardoso (Universidade Federal de Campina Grande) • Daniel Palomar (The Hong Kong University of Science and Technology)

Thresholding Bandit with Optimal Aggregate Regret

Chao Tao (Indiana University Bloomington) • Saúl A Blanco (Indiana University) • Jian Peng (University of Illinois at Urbana-Champaign) • Yuan Zhou (Indiana University Bloomington)

Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks

Yuanzhi Li (Princeton) • Colin Wei (Stanford University) • Tengyu Ma (Stanford)

Rethinking Kernel Methods for Node Representation Learning on Graphs

Yu Tian (Rutgers) • Long Zhao (Rutgers University) • Xi Peng (University of Delaware) • Dimitris Metaxas (Rutgers University)

Causal Misidentification in Imitation Learning

Pim de Haan (University of Amsterdam, visiting at UC Berkeley) • Dinesh Jayaraman (UC Berkeley) • Sergey Levine (UC Berkeley)

Optimizing Generalized PageRank Methods for Seed-Expansion Community Detection

Pan Li (Stanford) • I Chien (UIUC) • Olgica Milenkovic (University of Illinois at Urbana-Champaign)

The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data

Amanda Gentzel (UMass Amherst) • Dan Garant (C&S Wholesale Grocers) • David Jensen (Univ. of Massachusetts)

Dimension-Free Bounds for Low-Precision Training

Zheng Li (Tsinghua University) • Christopher De Sa (Cornell)

Concentration of risk measures: A Wasserstein distance approach

Sanjay P. Bhat (Tata Consultancy Services Limited) • Prashanth L.A. (IIT Madras)

Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

Lantao Yu (Stanford University) • Tianhe Yu (Stanford University) • Chelsea Finn (Stanford University) • Stefano Ermon (Stanford)

Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction

Aviral Kumar (UC Berkeley) • Justin Fu (UC Berkeley) • Matthew Soh (UC Berkeley) • George Tucker (Google Brain) • Sergey Levine (UC Berkeley)

Bayesian Optimization with Unknown Search Space

Huong Ha (Deakin University) • Santu Rana (Deakin University) • Sunil Gupta (Deakin University) • Thanh Nguyen (Deakin University) • Hung Tran-The (Deakin University) • Svetha Venkatesh (Deakin University)

On the Downstream Performance of Compressed Word Embeddings

Avner May (Stanford University) • Jian Zhang (Stanford University) • Tri Dao (Stanford University) • Christopher Ré (Stanford)

Multivariate Distributionally Robust Convex Regression under Absolute Error Loss

Jose Blanchet (Stanford University) • Peter W Glynn (Stanford University) • Jun Yan (Stanford) • Zhengqing Zhou (Stanford University)

Neural Relational Inference with Fast Modular Meta-learning

Ferran Alet (MIT) • Erica Weng (MIT) • Tomás Lozano-Pérez (MIT) • Leslie Kaelbling (MIT)

Gradient based sample selection for online continual learning

Rahaf Aljundi (KU Leuven, Belgium) • Min Lin (MILA) • Baptiste Goujaud (MILA) • Yoshua Bengio (Mila)

Attribution-Based Confidence Metric For Deep Neural Networks

Susmit Jha (SRI International) • Sunny Raj (University of Central Florida) • Steven Fernandes (University of Central Florida) • Sumit Jha (University of Central Florida) • Somesh Jha (University of Wisconsin, Madison) • Brian Jalaian (U.S. Army Research Laboratory) • Gunjan Verma (U.S. Army Research Laboratory) • Ananthram Swami (Army Research Laboratory, Adelphi)

Theoretical evidence for adversarial robustness through randomization

Rafael Pinot (Dauphine University - CEA LIST Institute) • Laurent Meunier (Dauphine University - FAIR Paris) • Alexandre Araujo (Université Paris-Dauphine - Wavestone) • Hisashi Kashima (Kyoto University/RIKEN Center for AIP) • Florian Yger (Université Paris-Dauphine) • Cedric Gouy-Pailler (CEA) • Jamal Atif (Université Paris-Dauphine)

Online Continual Learning with Maximal Interfered Retrieval

Rahaf Aljundi (KU Leuven, Belgium) • Eugene Belilovsky (University of Montreal) • Tinne Tuytelaars (KU Leuven) • Laurent Charlin (MILA / U.Montreal) • Massimo Caccia (MILA) • Min Lin (MILA) • Lucas Page-Caccia (McGill University)

Neural Attribution for Semantic Bug-Localization in Student Programs

Rahul Gupta (Indian Institute of Science) • Aditya Kanade (Indian Institute of Science) • Shirish Shevade (iisc)

Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates

Carlos Riquelme (Google Brain) • Hugo Penedones (Google DeepMind) • Damien Vincent (Google Brain) • Hartmut Maennel (Google) • Sylvain Gelly (Google Brain (Zurich)) • Timothy A Mann (DeepMind) • Andre Barreto (DeepMind) • Gergely Neu (Universitat Pompeu Fabra)

SPoC: Search-based Pseudocode to Code

Sumith Kulal (Stanford University) • Panupong Pasupat (Stanford University) • Kartik Chandra (Stanford University) • Mina Lee (Stanford University) • Oded Padon (Stanford University) • Alex Aiken (Stanford University) • Percy Liang (Stanford University)

Generative Modeling by Estimating Gradients of the Data Distribution

Yang Song (Stanford University) • Stefano Ermon (Stanford)

Adversarial Music: Real world Audio Adversary against Wake-word Detection System

Juncheng Li (Carnegie Mellon University) • Shuhui Qu (Stanford University) • Xinjian Li (Carnegie Mellon University) • Joseph C Szurley (Bosch Center for Artificial Intelligence) • J. Zico Kolter (Carnegie Mellon University / Bosch Center for AI) • Florian Metze (Carnegie Mellon University)

Prediction of Spatial Point Processes: Regularized Method with Out-of-Sample Guarantees

Muhammad Osama (Uppsala University) • Dave Zachariah (Uppsala University) • Peter Stoica (Uppsala University)

Debiased Bayesian inference for average treatment effects

Kolyan Ray (King's College London) • Botond Szabo (Leiden University)

Margin-Based Generalization Lower Bounds for Boosted Classifiers

Allan Grønlund (Aarhus University, MADALGO) • Lior Kamma (Aarhus University) • Kasper Green Larsen (Aarhus University, MADALGO) • Alexander Mathiasen (Aarhus University) • Jelani Nelson ()

Connections Between Mirror Descent, Thompson Sampling and the Information Ratio

Julian Zimmert (University of Copenhagen) • Tor Lattimore (DeepMind)

Graph Transformer Networks

Seongjun Yun (Korea university) • Minbyul Jeong (Korea university) • Raehyun Kim (Korea university) • Jaewoo Kang (Korea University) • Hyunwoo Kim (Korea University)

Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder

Ji Feng (Sinovation Ventures) • Qi-Zhi Cai (sinovation ventures) • Zhi-Hua Zhou (Nanjing University)

The Impact of Regularization on High-dimensional Logistic Regression

Fariborz Salehi (California Institute of Technology) • Ehsan Abbasi (Caltech) • Babak Hassibi (Caltech)

Adaptive Density Estimation for Generative Models

Thomas LUCAS (Inria Grenoble) • Konstantin Shmelkov (Huawei) • Karteek Alahari (Inria) • Cordelia Schmid (Inria / Google) • Jakob Verbeek (INRIA)

Fast and Provable ADMM for Learning with Generative Priors

Fabian Latorre Gomez (EPFL) • Armin eftekhari (EPFL) • Volkan Cevher (EPFL)

Weighted Linear Bandits for Non-Stationary Environments

Yoan Russac (Ecole Normale Supérieure) • Claire Vernade (Google DeepMind) • Olivier Cappé (CNRS)

Improved Regret Bounds for Bandit Combinatorial Optimization

Shinji Ito (NEC Corporation, University of Tokyo) • Daisuke Hatano (RIKEN AIP) • Hanna Sumita (Tokyo Metropolitan University) • Kei Takemura (NEC Corporation) • Takuro Fukunaga (Chuo University, JST PRESTO, RIKEN AIP) • Naonori Kakimura (Keio University) • Ken-Ichi Kawarabayashi (National Institute of Informatics)

Pareto Multi-Task Learning

Xi Lin (City University of Hong Kong) • Huiling Zhen (KU Leuven) • Zhenhua Li (National University of Singapore) • Qing-Fu Zhang () • Sam Kwong (City Univeristy of Hong Kong)

SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits

Etienne Boursier (ENS Paris Saclay) • Vianney Perchet (ENS Paris-Saclay & Criteo AI Lab)

Novel positional encodings to enable tree-based transformers

Vighnesh Shiv (Microsoft Research) • Chris Quirk (Microsoft Research)

A Domain Agnostic Measure for Monitoring and Evaluating GANs

Paulina Grnarova (ETH Zurich) • Yehuda Kfir Levy (ETH) • Aurelien Lucchi (ETH Zurich) • Nathanael Perraudin (Swiss Data Science Center - EPFL / ETH Zurich) • Ian Goodfellow (Google) • Thomas Hofmann (ETH Zurich) • Andreas Krause (ETH Zurich)

Submodular Function Minimization with Noisy Evaluation Oracle

Shinji Ito (NEC Corporation, University of Tokyo)

Counting the Optimal Solutions in Graphical Models

Radu Marinescu (IBM Research) • Rina Dechter (UCI)

Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach

Shuyue Hu (the Chinese University of Hong Kong) • Chin-wing Leung (The Chinese University of Hong Kong) • Ho-fung Leung (The Chinese University of Hong Kong)

Deep Multimodal Multilinear Fusion with High-order Polynomial Pooling

Ming Hou (RIKEN AIP) • Jiajia Tang (Hangzhou Dianzi University / RIKEN AIP) • Jianhai Zhang (Hangzhou Dianzi University) • Wanzeng Kong (Hangzhou Dianzi University) • Qibin Zhao (RIKEN AIP)

Bootstrapping Upper Confidence Bound

Botao Hao (Purdue University) • Yasin Abbasi (Adobe Research) • Zheng Wen (Adobe Research) • Guang Cheng (Purdue University)

Integer Discrete Flows and Lossless Compression

Emiel Hoogeboom (University of Amsterdam) • Jorn Peters (University of Amsterdam) • Rianne van den Berg (Google Brain) • Max Welling (University of Amsterdam / Qualcomm AI Research)

Structured Prediction with Projection Oracles

Mathieu Blondel (NTT)

Primal Dual Formulation For Deep Learning With Constraints

Yatin Nandwani (Indian Institute Of Technology Delhi) • Abhishek Pathak (Indian Institute Of Technology, Delhi) • Mausam (IIT Dehli) • Parag Singla (Indian Institute of Technology Delhi)

Screening Sinkhorn Algorithm for Regularized Optimal Transport

Mokthar Z. Alaya (University of Rouen) • Maxime Berar (Université de Rouen) • Gilles Gasso (LITIS - INSA de Rouen) • Alain Rakotomamonjy (Université de Rouen Normandie Criteo AI Lab)

PAC-Bayes Un-Expected Bernstein Inequality

Zakaria Mhammedi (The Australian National University) • Peter Grünwald (CWI and Leiden University) • Benjamin Guedj (Inria & University College London)

Are Labels Required for Improving Adversarial Robustness?

Jean-Baptiste Alayrac (Deepmind) • Jonathan Uesato (DeepMind) • Po-Sen Huang (DeepMind) • Alhussein Fawzi (DeepMind) • Robert Stanforth (DeepMind) • Pushmeet Kohli (DeepMind)

Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies

Yonathan Efroni (Technion) • Nadav Merlis (Technion) • Mohammad Ghavamzadeh (Facebook AI Research) • Shie Mannor (Technion)

Multi-objective Bayesian optimisation with preferences over objectives

Majid Abdolshah (Deakin University) • Alistair Shilton (Deakin University) • Santu Rana (Deakin University) • Sunil Gupta (Deakin University) • Svetha Venkatesh (Deakin University)

Think out of the "Box": Generically-Constrained Asynchronous Composite Optimization and Hedging

Pooria Joulani (DeepMind) • András György (DeepMind) • Csaba Szepesvari (DeepMind/University of Alberta)

Calibration tests in multi-class classification: A unifying framework

David Widmann (Uppsala University) • Fredrik Lindsten (Linköping Universituy) • Dave Zachariah (Uppsala University)

Classification Accuracy Score for Conditional Generative Models

Suman Ravuri (DeepMind) • Oriol Vinyals (Google DeepMind)

Theoretical Analysis Of Adversarial Learning: A Minimax Approach

Zhuozhuo Tu (The University of Sydney) • Jingwei Zhang (Hong Kong University of Science and Technology & University of Sydney) • Dacheng Tao (University of Sydney)

Multiagent Evaluation under Incomplete Information

Mark Rowland (DeepMind) • Shayegan Omidshafiei (DeepMind) • Karl Tuyls (DeepMind) • Julien Perolat (DeepMind) • Michal Valko (DeepMind Paris and Inria Lille - Nord Europe) • Georgios Piliouras (Singapore University of Technology and Design) • Remi Munos (DeepMind)

Tree-Sliced Variants of Wasserstein Distances

Tam Le (RIKEN AIP) • Makoto Yamada (Kyoto University / RIKEN AIP) • Kenji Fukumizu (Institute of Statistical Mathematics / Preferred Networks / RIKEN AIP) • Marco Cuturi (Google and CREST/ENSAE)

Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration

Meelis Kull (University of Tartu) • Miquel Perello Nieto (University of Bristol) • Markus Kängsepp (University of Tartu) • Telmo Silva Filho (Universidade Federal da Paraíba) • Hao Song (University of Bristol) • Peter Flach (University of Bristol)

Comparing distributions: ℓ1ℓ1 geometry improves kernel two-sample testing

meyer scetbon (ENS CACHAN) • Gael Varoquaux (Parietal Team, INRIA)

Robustness Verification of Tree-based Models

Hongge Chen (MIT) • Huan Zhang (UCLA) • Si Si (Google Research) • Yang Li (Google) • Duane Boning (Massachusetts Institute of Technology) • Cho-Jui Hsieh (UCLA)

Towards Interpretable Reinforcement Learning Using Attention Augmented Agents

Alexander Mott (DeepMind) • Daniel Zoran (DeepMind) • Mike Chrzanowski (DeepMind) • Daan Wierstra (DeepMind Technologies) • Danilo Jimenez Rezende (Google DeepMind)

Fast and Accurate Stochastic Gradient Estimation

Beidi Chen (Rice University) • Yingchen Xu (Rice University) • Anshumali Shrivastava (Rice University)

Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning

Igor Colin (Huawei) • Ludovic DOS SANTOS (Huawei) • Kevin Scaman (Huawei Technologies, Noah's Ark)

Root Mean Square Layer Normalization

Biao Zhang (University of Edinburgh) • Rico Sennrich (University of Edinburgh)

Universality in Learning from Linear Measurements

Ehsan Abbasi (Caltech) • Fariborz Salehi (California Institute of Technology) • Babak Hassibi (Caltech)

Planning in Entropy-Regularized Markov Decision Processes and Games

Jean-Bastien Grill (Google DeepMind) • Omar Darwiche Domingues (Inria) • Pierre Menard (Inria) • Remi Munos (DeepMind) • Michal Valko (DeepMind Paris and Inria Lille - Nord Europe)

Exponentially convergent stochastic k-PCA without variance reduction

Cheng Tang (Amazon)

R2D2: Reliable and Repeatable Detectors and Descriptors for Joint Sparse Keypoint Detection and Local Feature Extraction

Jerome Revaud (Naver Labs Europe) • Cesar De Souza (NAVER LABS Europe) • Martin Humenberger (Naver Labs Europe) • Philippe Weinzaepfel (NAVER LABS Europe)

Selective Sampling-based Scalable Sparse Subspace Clustering

Shin Matsushima (The University of Tokyo) • Maria Brbic (Stanford University)

A General Framework for Efficient Symmetric Property Estimation

Moses Charikar (Stanford University) • Kirankumar Shiragur (Stanford University) • Aaron Sidford (Stanford)

Structured Variational Inference in Continuous Cox Process Models

Virginia Aglietti (University of Warwick) • Edwin Bonilla (CSIRO's Data61) • Theodoros Damoulas (University of Warwick The Alan Turing Institute) • Sally Cripps (University of Sydney)

Generalization of Reinforcement Learners with Working and Episodic Memory

Meire Fortunato (DeepMind) • Melissa Tan (Deepmind) • Ryan Faulkner (Deepmind) • Steven Hansen (DeepMind) • Adrià Puigdomènech Badia (Google DeepMind) • Gavin Buttimore (DeepMind) • Charles Deck (Deepmind) • Joel Leibo (DeepMind) • Charles Blundell (DeepMind)

Distribution Learning of a Random Spatial Field with a Location-Unaware Mobile Sensor

Meera V Pai (Indian Institute of Technology Bombay) • Animesh Kumar (Indian Institute of Technology Bombay)

Hindsight Credit Assignment

Anna Harutyunyan (DeepMind) • Will Dabney (DeepMind) • Thomas Mesnard (DeepMind) • Mohammad Gheshlaghi Azar (DeepMind) • Bilal Piot (DeepMind) • Nicolas Heess (Google DeepMind) • Hado van Hasselt (DeepMind) • Gregory Wayne (Google DeepMind) • Satinder Singh (DeepMind) • Doina Precup (DeepMind) • Remi Munos (DeepMind)

Efficient Identification in Linear Structural Causal Models with Instrumental Cutsets

Daniel Kumor (Purdue) • Bryant Chen (Brex) • Elias Bareinboim (Purdue)

Kernelized Bayesian Softmax for Text Generation

NING MIAO (Peking University) • Hao Zhou (Bytedance) • Chengqi Zhao (Bytedance) • Wenxian Shi (Bytedance) • Yitan Li (ByteDance.Inc) • Lei Li (Bytedance)

When to Trust Your Model: Model-Based Policy Optimization

Michael Janner (UC Berkeley) • Justin Fu (UC Berkeley) • Marvin Zhang (UC Berkeley) • Sergey Levine (UC Berkeley)

Correlation Clustering with Adaptive Similarity Queries

Marco Bressan (Sapienza University of Rome) • Nicolò Cesa-Bianchi (Università degli Studi di Milano) • Andrea Paudice (University of Milan) • Fabio Vitale (Sapienza University of Rome)

Control What You Can: Intrinsically Motivated Task-Planning Agent

Sebastian Blaes (Max Planck Institute for Intelligent Systems) • Marin Vlastelica Pogančić (Max-Planck Institute for Intelligent Systems, Tuebingen) • Jia-Jie Zhu (Max Planck Institute for Intelligent Systems) • Georg Martius (MPI for Intelligent Systems)

Selecting causal brain features with a single conditional independence test per feature

Atalanti Mastakouri (Max Planck Institute for Intelligent Systems) • Bernhard Schölkopf (MPI for Intelligent Systems) • Dominik Janzing (Amazon)

Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders

Emile Mathieu () • Charline Le Lan (University of Oxford) • Chris J. Maddison (Institute for Advanced Study, Princeton) • Ryota Tomioka (Microsoft Research Cambridge) • Yee Whye Teh (University of Oxford, DeepMind)

A Generic Acceleration Framework for Stochastic Composite Optimization

Andrei Kulunchakov (Inria) • Julien Mairal (Inria)

Beating SGD Saturation with Tail-Averaging and Minibatching

Nicole Muecke (University of Stuttgart) • Gergely Neu (Universitat Pompeu Fabra) • Lorenzo Rosasco (University of Genova- MIT - IIT)

Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond

Arindam Banerjee (Voleon) • Qilong Gu (University of Minnesota Twin Cities) • Vidyashankar Sivakumar (University of Minnesota) • Steven Wu (Microsoft Research)

Continuous-time Models for Stochastic Optimization Algorithms

Antonio Orvieto (ETH Zurich) • Aurelien Lucchi (ETH Zurich)

Curriculum-guided Hindsight Experience Replay

Meng Fang (Tencent) • Tianyi Zhou (University of Washington, Seattle) • Yali Du (University of Technology Sydney) • Lei Han (Rutgers University) • Zhengyou Zhang ()

Implicit Semantic Data Augmentation for Deep Networks

Yulin Wang (Tsinghua University) • Xuran Pan (Tsinghua University) • Shiji Song (Department of Automation, Tsinghua University) • Hong Zhang (Baidu Inc.) • Gao Huang (Tsinghua) • Cheng Wu (Tsinghua)

MetaInit: Initializing learning by learning to initialize

Yann Dauphin (Google AI) • Samuel Schoenholz (Google Brain)

Scalable Deep Generative Relational Model with High-Order Node Dependence

Xuhui Fan (University of New South Wales) • Bin Li (Fudan University) • Caoyuan Li (UTS) • Scott SIsson (University of New South Wales, Sydney) • Ling Chen (" University of Technology, Sydney, Australia")

Random Path Selection for Continual Learning

Jathushan Rajasegaran (IIAI) • Munawar Hayat (IIAI) • Salman Khan (IIAI) • Fahad Shahbaz Khan (Inception Institute of Artificial Intelligence) • Ling Shao (Inception Institute of Artificial Intelligence)

Efficient Algorithms for Smooth Minimax Optimization

Kiran Thekumparampil (Univ. of Illinois at Urbana-Champaign) • Prateek Jain (Microsoft Research) • Praneeth Netrapalli (Microsoft Research) • Sewoong Oh (University of Washington)

Shadowing Properties of Optimization Algorithms

Antonio Orvieto (ETH Zurich) • Aurelien Lucchi (ETH Zurich)

Causal Regularization

Dominik Janzing (Amazon)

Learning Hawkes Processes from a handful of events

Farnood Salehi (EPFL) • William Trouleau (EPFL) • Matthias Grossglauser (EPFL) • Patrick Thiran (EPFL)

Unsupervised Object Segmentation by Redrawing

Mickael Chen (Université Pierre et Marie Curie) • Thierry Artières (Aix-Marseille Université) • Ludovic Denoyer (Facebook - FAIR)

Regret Bounds for Learning State Representations in Reinforcement Learning

Ronald Ortner (Montanuniversitaet Leoben) • Matteo Pirotta (Facebook AI Research) • Alessandro Lazaric (Facebook Artificial Intelligence Research) • Ronan Fruit (Inria Lille) • Odalric-Ambrym Maillard (INRIA)

Band-Limited Gaussian Processes: The Sinc Kernel

Felipe Tobar (Universidad de Chile)

Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification

Evgenii Chzhen (Université Paris-Est) • Christophe Denis (Universit? Paris Est) • Mohamed Hebiri () • Luca Oneto (University of Genoa) • Massimiliano Pontil (IIT)

Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning

Valerio Perrone (Amazon) • Huibin Shen (Amazon) • Matthias Seeger (Amazon) • Cedric Archambeau (Amazon) • Rodolphe Jenatton (Amazon)

Feedforward Bayesian Inference for Crowdsourced Classification

Edoardo Manino (University of Southampton) • Long Tran-Thanh (University of Southampton) • Nicholas Jennings (Imperial College, London)

Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation

Ruibo Tu (KTH Royal Institute of Technology) • Kun Zhang (CMU) • Bo Bertilson (KI Karolinska Institutet) • Hedvig Kjellstrom (KTH Royal Institute of Technology) • Cheng Zhang (Microsoft)

Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs

Jonas Kubilius (Massachusetts Institute of Technology) • Martin Schrimpf (MIT) • Ha Hong (Bay Labs Inc.) • Najib Majaj (NYU) • Rishi Rajalingham (MIT) • Elias Issa (Columbia University) • Kohitij Kar (MIT) • Pouya Bashivan (Massachusetts Institute of Technology) • Jonathan Prescott-Roy (MIT) • Kailyn Schmidt (MIT) • Aran Nayebi (Stanford University) • Daniel Bear (Stanford University) • Daniel Yamins (Stanford University) • James J DiCarlo (Massachusetts Institute of Technology)

k-Means Clustering of Lines for Big Data

Yair Marom (University of Haifa) • Dan Feldman (University of Haifa)

Random projections and sampling algorithms for clustering of high-dimensional polygonal curves

Stefan Meintrup (TU Dortmund) • Alexander Munteanu (TU Dortmund) • Dennis Rohde (TU Dortmund)

Recurrent Space-time Graph Neural Networks

Andrei Nicolicioiu (Bitdefender) • Iulia Duta (Bitdefender) • Marius Leordeanu (Institute of Mathematics of the Romanian Academy)

Uncertainty on Asynchronous Event Prediction

Bertrand Charpentier (Technical University of Munich) • Marin Biloš (Technical University of Munich) • Stephan Günnemann (Technical University of Munich)

Accurate, reliable and fast robustness evaluation

Wieland Brendel (AG Bethge, University of Tübingen) • Jonas Rauber (University of Tübingen) • Matthias Kümmerer (University of Tübingen) • Ivan Ustyuzhaninov (University of Tübingen) • Matthias Bethge (University of Tübingen)

Sparse High-Dimensional Isotonic Regression

David Gamarnik (Massachusetts Institute of Technology) • Julia Gaudio (Massachusetts Institute of Technology)

Triad Constraints for Learning Causal Structure of Latent Variables

Ruichu Cai (Guangdong University of Technology) • Feng Xie (Guangdong University of Technology) • Clark Glymour (Carnegie Mellon University) • Zhifeng Hao (Guangdong University of Technology) • Kun Zhang (CMU)

On the Inductive Bias of Neural Tangent Kernels

Alberto Bietti (Inria) • Julien Mairal (Inria)

Cross-Domain Transferable Perturbations

Muzammal Naseer (Australian National University (ANU)) • Salman Khan (IIAI) • Muhammad Haris Khan (Inception Institute of Artificial Intelligence) • Fahad Shahbaz Khan (Inception Institute of Artificial Intelligence) • Fatih Porikli (ANU)

Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices

Don Dennis (Microsoft Research) • Durmus Alp Emre Acar (Boston University) • Vikram Mandikal (Microsoft Research) • Vinu Sankar Sadasivan (Indian Institute of Technology Gandhinagar) • Venkatesh Saligrama (Boston University) • Harsha Vardhan Simhadri (Microsoft Research India) • Prateek Jain (Microsoft Research)

Kernel quadrature with DPPs

Ayoub Belhadji (Ecole Centrale de Lille) • Rémi Bardenet (University of Lille) • Pierre Chainais (Centrale Lille / CRIStAL CNRS UMR 9189)

REM: From Structural Entropy to Community Structure Deception

Yiwei Liu (Beijing institute of technology) • Jiamou Liu (University of Auckland) • Zijian Zhang (Beijing Institute of Technology) • Liehuang Zhu (Beijing Institute of Technology) • Angsheng Li (Beihang University)

Sim2real transfer learning for 3D pose estimation: motion to the rescue

Carl Doersch (DeepMind) • Andrew Zisserman (DeepMind & University of Oxford)

Self-Supervised Deep Learning on Point Clouds by Reconstructing Space

Bjarne Sievers (Hasso-Plattner-Institut) • Jonathan Sauder (Hasso Plattner Institute)

Piecewise Strong Convexity of Neural Networks

Tristan Milne (University of Toronto)

Minimum Stein Discrepancy Estimators

Alessandro Barp (Imperial College London) • Francois-Xavier Briol (University of Cambridge) • Andrew Duncan (Imperial College London) • Mark Girolami (University of Cambridge) • Lester Mackey (Microsoft Research)

Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes

James Bailey (Singapore University of Technology and Design) • Georgios Piliouras (Singapore University of Technology and Design)

Generalization Bounds for Neural Networks via Approximate Description Length

Amit Daniely (Google Research) • Elad Granot (Hebrew University)

Provably robust boosted decision stumps and trees against adversarial attacks

Maksym Andriushchenko (University of Tübingen / EPFL) • Matthias Hein (University of Tübingen)

Convergence of Adversarial Training in Overparametrized Neural Networks

Ruiqi Gao (Peking University) • Tianle Cai (Peking University) • Haochuan Li (MIT) • Cho-Jui Hsieh (UCLA) • Liwei Wang (Peking University) • Jason Lee (USC)

A Composable Specification Language for Reinforcement Learning Tasks

Kishor Jothimurugan (University of Pennsylvania) • Rajeev Alur (University of Pennsylvania ) • Osbert Bastani (University of Pennysylvania)

The Option Keyboard: Combining Skills in Reinforcement Learning

Andre Barreto (DeepMind) • Diana Borsa (DeepMind) • Shaobo Hou (DeepMind) • Gheorghe Comanici (Google) • Eser Aygun (Google Canada) • Philippe Hamel (Google) • Daniel Toyama (DeepMind Montreal) • Jonathan J Hunt (DeepMind) • Shibl Mourad (Google) • David Silver (DeepMind) • Doina Precup (DeepMind)

Unified Language Model Pre-training for Natural Language Understanding and Generation

Li Dong (Microsoft Research) • Nan Yang (Microsoft Research Asia) • Wenhui Wang (Microsoft Research) • Furu Wei (Microsoft Research Asia) • Xiaodong Liu (Microsoft) • Yu Wang (Microsoft Research) • Jianfeng Gao (Microsoft Research, Redmond, WA) • Ming Zhou (Microsoft Research) • Hsiao-Wuen Hon (Microsoft Research)

Learning to Correlate in Multi-Player General-Sum Sequential Games

Andrea Celli (Politecnico di Milano) • Alberto Marchesi (Politecnico di Milano) • Tommaso Bianchi (Politecnico di Milano) • Nicola Gatti (Politecnico di Milano)

Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match

Amin Karbasi (Yale) • Hamed Hassani (UPenn) • Aryan Mokhtari (UT Austin) • Zebang Shen (Zhejiang University)

Generative Well-intentioned Networks

Justin T Cosentino (Tsinghua University) • Jun Zhu (Tsinghua University)

Online-Within-Online Meta-Learning

Giulia Denevi (IIT/UNIGE) • Dimitris Stamos (University College London) • Carlo Ciliberto (Imperial College London) • Massimiliano Pontil (IIT & UCL)

Learning step sizes for unfolded sparse coding

Pierre Ablin (Inria) • Thomas Moreau (Inria) • Mathurin Massias (Inria) • Alexandre Gramfort (INRIA, Université Paris-Saclay)

Biases for Emergent Communication in Multi-agent Reinforcement Learning

Tom Eccles (DeepMind) • Yoram Bachrach () • Guy Lever (Google DeepMind) • Angeliki Lazaridou (DeepMind) • Thore Graepel (DeepMind)

Episodic Memory in Lifelong Language Learning

Cyprien de Masson d'Autume (Google DeepMind) • Sebastian Ruder (DeepMind) • Lingpeng Kong (DeepMind) • Dani Yogatama (DeepMind)

A Simple Baseline for Bayesian Uncertainty in Deep Learning

Wesley J Maddox (Cornell University) • Pavel Izmailov (CORNELL UNIVERSITY) • Timur Garipov (Moscow State University) • Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow) • Andrew Wilson (Cornell University)

Communication-efficient Distributed SGD with Sketching

Nikita Ivkin (Amazon) • Daniel Rothchild (UC Berkeley) • Md Enayat Ullah (Johns Hopkins University) • Vladimir braverman (Johns Hopkins University) • Ion Stoica (UC Berkeley) • Raman Arora (Johns Hopkins University)

Modeling Conceptual Understanding in Image Reference Games

Rodolfo Corona Rodriguez (University of Amsterdam) • Zeynep Akata (University of Amsterdam) • Stephan Alaniz (University of Amsterdam)

Kalman Filter, Sensor Fusion, and Constrained Regression: Equivalences and Insights

David Farrow (Carnegie Mellon University) • Maria Jahja (Carnegie Mellon University) • Roni Rosenfeld (Carnegie Mellon University) • Ryan Tibshirani (Carnegie Mellon University)

Near Neighbor: Who is the Fairest of Them All?

Sepideh Mahabadi (Toyota Technological Institute at Chicago) • Sariel Har-Peled (University of Illinois at Urbana-Champaign)

Outlier-robust estimation of a sparse linear model using ℓ1ℓ1-penalized Huber's MM-estimator

Arnak Dalalyan (ENSAE ParisTech) • Philip Thompson (ENSAE ParisTech - Centre for Research in Economics and Statistic)

Learning nonlinear level sets for dimensionality reduction in function approximation

Guannan Zhang (Oak Ridge National Laboratory) • Jiaxin Zhang (Oak Ridge National Laboratory) • Jacob Hinkle (Oak Ridge National Lab)

Assessing Social and Intersectional Biases in Contextualized Word Representations

Yi Chern Tan (Yale University) • L. Elisa Celis (Yale University)

Online Convex Matrix Factorization with Representative Regions

Jianhao Peng (University of Illinois at Urbana Champaign) • Olgica Milenkovic (University of Illinois at Urbana-Champaign) • Abhishek Agarwal (University of Illinois at Urbana Champaign)

Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game

Ngoc-Trung Tran (Singapore University of Technology and Design) • Viet-Hung Tran (Singapore University of Technology and Design) • Bao-Ngoc Nguyen (Singapore University of Technology and Design) • Linxiao Yang (University of Electronic Science and Technology of China; Singapore University of Technology and Design) • Ngai-Man Cheung (Singapore University of Technology and Design)

Simultaneous Matching and Ranking as end-to-end Deep Classification: A Case study of Information Retrieval with 50M Documents

Tharun Kumar Reddy Medini (Rice University) • Qixuan Huang (Rice University) • Yiqiu Wang (Massachusetts Institute of Technology) • Vijai Mohan (www.amazon.com) • Anshumali Shrivastava (Rice University)

A Fourier Perspective on Model Robustness in Computer Vision

Dong Yin (UC Berkeley) • Raphael Gontijo Lopes (Google Brain) • Ekin Dogus Cubuk (Google Brain) • Justin Gilmer (Google Brain) • Jon Shlens (Google Research)

The continuous Bernoulli: fixing a pervasive error in variational autoencoders

Gabriel Loaiza-Ganem (Columbia University) • John Cunningham (University of Columbia)

Privacy Amplification by Mixing and Diffusion Mechanisms

Borja Balle (Amazon Research Cambridge) • Gilles Barthe (Max Planck Institute) • Marco Gaboardi (Univeristy at Buffalo) • Joseph Geumlek (UCSD)

Variance Reduction in Bipartite Experiments through Correlation Clustering

Jean Pouget-Abadie (Harvard University) • Kevin Aydin (Google) • Warren Schudy (Google) • Kay Brodersen (Google) • Vahab Mirrokni (Google Research NYC)

Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning

Mahmoud Assran (McGill University / Facebook AI Research) • Joshua Romoff (McGill University) • Nicolas Ballas (Facebook FAIR) • Joelle Pineau (Facebook) • Mike Rabbat (Facebook FAIR)

Metalearned Neural Memory

Tsendsuren Munkhdalai (Microsoft Research) • Alessandro Sordoni (Microsoft Research Montreal) • TONG WANG (Microsoft Research Montreal) • Adam Trischler (Microsoft)

Learning Multiple Markov Chains via Adaptive Allocation

Mohammad Sadegh Talebi (Inria) • Odalric-Ambrym Maillard (INRIA)

Diffusion Improves Graph Learning

Johannes Klicpera (Technical University of Munich) • Stefan Weißenberger (Technical University of Munich) • Stephan Günnemann (Technical University of Munich)

Deep Random Splines for Point Process Intensity Estimation of Neural Population Data

Gabriel Loaiza-Ganem (Columbia University) • John Cunningham (University of Columbia) • Sean Perkins (Columbia University) • Karen Schroeder (Columbia University) • Mark Churchland (Columbia University)

Variational Bayes under Model Misspecification

Yixin Wang (Columbia University) • David Blei (Columbia University)

On the Importance of Initialization in Optimization for Deep Linear Neural Networks

Lei Wu (Princeton University) • Qingcan Wang (PACM, Princeton University) • Chao Ma (Princeton University)

On Differentially Private Graph Sparsification and Applications

Raman Arora (Johns Hopkins University) • Jalaj Upadhyay (Johns Hopkins University)

Manifold denoising by Nonlinear Robust Principal Component Analysis

Rongrong Wang (Michigan State University) • Ming Yan (Michigan State University) • He Lyu (Michigan State University) • Yuying Xie (Michigan State University) • Ningyu Sha (MSU) • Shuyang Qin (Michigan State University)

Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes

Junzhe Zhang (Purdue University) • Elias Bareinboim (Purdue)

ODE2VAE: Deep generative second order ODEs with Bayesian neural networks

Cagatay Yildiz (Aalto University) • Markus Heinonen (Aalto University) • Harri Lahdesmaki (Aalto University)

Optimal Sampling and Clustering in the Stochastic Block Model

Se-Young Yun (KAIST) • Alexandre Proutiere (KTH)

Recurrent Kernel Networks

Dexiong Chen (Inria) • Laurent Jacob (CNRS) • Julien Mairal (Inria)

Cold Case: The Lost MNIST Digits

Chhavi Yadav (Walmart Labs, NYU) • Leon Bottou (Facebook AI Research)

Hierarchical Optimal Transport for Multimodal Distribution Alignment

John Lee (Georgia Institute of Technology) • Max Dabagia (Georgia Institute of Technology) • Eva Dyer (Georgia Tech) • Christopher Rozell (Georgia Institute of Technology)

Exploration via Hindsight Goal Generation

Zhizhou Ren (Tsinghua University) • Kefan Dong (Tsinghua University) • Yuan Zhou (Indiana University Bloomington) • Qiang Liu (UT Austin) • Jian Peng (University of Illinois at Urbana-Champaign)

Shaping Belief States with Generative Environment Models for RL

Karol Gregor (DeepMind) • Danilo Jimenez Rezende (Google DeepMind) • Frederic Besse (DeepMind) • Yan Wu (DeepMind) • Hamza Merzic (Deepmind) • Aaron van den Oord (Google Deepmind)

Globally Optimal Learning for Structured Elliptical Losses

Yoav Wald (Hebrew University) • Nofar Noy (Hebrew University) • Gal Elidan (Google) • Ami Wiesel (Google Research and The Hebrew University of Jerusalem, Israel)

Object landmark discovery through unsupervised adaptation

Enrique Sanchez (Samsung AI Centre) • Georgios Tzimiropoulos (University of Nottingham)

Specific and Shared Causal Relation Modeling and Mechanism-based Clustering

Biwei Huang (Carnegie Mellon University) • Kun Zhang (CMU) • Pengtao Xie (Petuum / CMU) • Mingming Gong (University of Melbourne) • Eric Xing (Petuum Inc.) • Clark Glymour (Carnegie Mellon University)

Search-Guided, Lightly-Supervised Training of Structured Prediction Energy Networks

Amirmohammad Rooshenas (University of Massachusetts, Amherst) • Dongxu Zhang (University of Massachusetts Amherst) • Gopal Sharma (University of Massachusetts Amherst) • Andrew McCallum (UMass Amherst)

Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functions

Ashia Wilson (UC Berkeley) • Lester Mackey (Microsoft Research) • Andre Wibisono ()

RUDDER: Return Decomposition for Delayed Rewards

José Arjona-Medina (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) • Michael Gillhofer (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) • Michael Widrich (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) • Thomas Unterthiner (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) • Johannes Brandstetter (LIT AI Lab / University Linz) • Sepp Hochreiter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria)

Graph Normalizing Flows

Jenny Liu (University of Toronto) • Aviral Kumar (UC Berkeley) • Jimmy Ba (University of Toronto / Vector Institute) • Jamie Kiros (Google Inc.) • Kevin Swersky (Google)

Explanations can be manipulated and geometry is to blame

Ann-Kathrin Dombrowski (TU Berlin) • Maximillian Alber (TU Berlin) • Christopher Anders (Technische Universität Berlin) • Marcel Ackermann (HHI) • Klaus-Robert Müller (TU Berlin) • Pan Kessel (TU Berlin)

Communication trade-offs for synchronized distributed SGD with large step size

Aymeric Dieuleveut (EPFL) • Kshitij Patel (Indian Institute of Technology Kanpur)

Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics

Giancarlo Kerg (MILA) • Kyle Goyette (University of Montreal) • Maximilian Puelma Touzel (Mila) • Gauthier Gidel (Mila) • Eugene Vorontsov (Polytechnique Montreal) • Yoshua Bengio (Mila) • Guillaume Lajoie (Université de Montréal / Mila)

No-Regret Learning in Unknown Games with Correlated Payoffs

Pier Giuseppe Sessa (ETH Zürich) • Ilija Bogunovic (ETH Zurich) • Maryam Kamgarpour (ETH Zürich) • Andreas Krause (ETH Zurich)

Alleviating Label Switching with Optimal Transport

Pierre Monteiller (ENS Ulm ) • Sebastian Claici (MIT) • Edward Chien (Massachusetts Institute of Technology) • Farzaneh Mirzazadeh (IBM Research, MIT-IBM Watson AI Lab) • Justin M Solomon (MIT) • Mikhail Yurochkin (IBM Research, MIT-IBM Watson AI Lab)

Paraphrase Generation with Latent Bag of Words

Yao Fu (Columbia University) • Yansong Feng (Peking University) • John Cunningham (University of Columbia)

An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors

Janardhan Kulkarni (MSR, Redmond) • Olga Ohrimenko (Microsoft Research) • Bolin Ding (Alibaba Group) • Sergey Yekhanin (Microsoft) • Joshua Allen (Microsoft) • Harsha Nori (Microsoft)

Compacting, Picking and Growing for Unforgetting Continual Learning

Ching-Yi Hung (Academia Sinica) • Cheng-Hao Tu (Academia Sinica) • Cheng-En Wu (Academia Sinica) • Chien-Hung Chen (Academia Sinica) • Yi-Ming Chan (Academia Sinica) • Chu-Song Chen (Academia Sinica)

Approximating Interactive Human Evaluation withSelf-Play for Open-Domain Dialog Systems

Asma Ghandeharioun (MIT) • Judy Hanwen Shen (Massachusetts Institute of Technology) • Natasha Jaques (MIT) • Craig Ferguson (MIT) • Noah Jones (MIT) • Agata Garcia (Massachusetts Institute of Technology) • Rosalind Picard (MIT Media Lab)

A New Distribution on the Simplex with Auto-Encoding Applications

Andrew Stirn (Columbia University) • Tony Jebara (Netflix) • David Knowles (Columbia University)

AutoPrun: Automatic Network Pruning by Regularizing Auxiliary Parameters

XIA XIAO (University of Connecticut) • Zigeng Wang (University of Connecticut) • Sanguthevar Rajasekaran (University of Connecticut)

A neurally plausible model learns successor representations in partially observable environments

Eszter Vértes (Gatsby Unit, UCL) • Maneesh Sahani (Gatsby Unit, UCL)

Learning about an exponential amount of conditional distributions

Mohamed Belghazi (University of Montreal) • Maxime Oquab (Facebook AI Research) • David Lopez-Paz (Facebook AI Research)

Towards modular and programmable architecture search

Renato Negrinho (Carnegie Mellon University) • Matthew Gormley (Carnegie Mellon University) • Geoffrey Gordon (MSR Montréal & CMU) • Darshan Patil (Carnegie Mellon University) • Nghia Le (Carnegie Mellon University) • Daniel Ferreira (TU Wien)

Towards Hardware-Aware Tractable Learning of Probabilistic Models

Laura I. Galindez Olascoaga (KU Leuven) • Wannes Meert (K.U.Leuven) • Marian Verhelst (KU Leuven) • Guy Van den Broeck (UCLA)

On Robustness to Adversarial Examples and Polynomial Optimization

Pranjal Awasthi (Rutgers University/Google) • Abhratanu Dutta (Northwestern University) • Aravindan Vijayaraghavan (Northwestern University)

Rand-NSG: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node

Suhas Jayaram Subramanya (Microsoft Research India) • Devvrit Lnu (BITS Pilani) • Harsha Vardhan Simhadri (Microsoft Research India) • Ravishankar Krishnawamy (Microsoft Research India)

A Solvable High-Dimensional Model of GAN

Chuang Wang (Institute of Automation, Chinese Academy of Sciences)

Using Embeddings to Correct for Unobserved Confounding in Networks

Victor Veitch (Columbia University) • Yixin Wang (Columbia University) • David Blei (Columbia University)

PolyTree framework for tree ensemble analysis

Igor E. Kuralenok (Experts League Ltd.) • Vasilii Ershov (Yandex) • Igor Labutin (Saint Petersburg campus of National Research University Higher School of Economics)

Bayesian Optimization under Heavy-tailed Payoffs

Sayak Ray Chowdhury (Indian Institute of Science) • Aditya Gopalan (Indian Institute of Science)

Combining Generative and Discriminative Models for Hybrid Inference

Victor Garcia Satorras (UPC) • Max Welling (University of Amsterdam / Qualcomm AI Research) • Zeynep Akata (University of Amsterdam)

A Graph Theoretic Additive Approximation of Optimal Transport

Nathaniel Lahn (Virginia Tech) • Deepika Mulchandani (Virginia Tech) • Sharath Raghvendra (Virginia Tech)

Adversarial Robustness through Local Linearization

Chongli Qin (DeepMind) • James Martens (DeepMind) • Sven Gowal (DeepMind) • Dilip Krishnan (Google) • Krishnamurthy Dvijotham (DeepMind) • Alhussein Fawzi (DeepMind) • Soham De (DeepMind) • Robert Stanforth (DeepMind) • Pushmeet Kohli (DeepMind)

Sampled softmax with random Fourier features

Ankit Singh Rawat (Google Research) • Jiecao Chen (Indiana University Bloomington) • Felix Xinnan Yu (Google Research) • Ananda Theertha Suresh (Google) • Sanjiv Kumar (Google Research)

Semi-flat minima and saddle points by embedding neural networks to overparameterization

Kenji Fukumizu (Institute of Statistical Mathematics / Preferred Networks / RIKEN AIP) • Shoichiro Yamaguchi (Preferred Networks) • Yoh-ichi Mototake (Institute of Statistical Mathematics) • Mirai Tanaka (The Institute of Statistical Mathematics / RIKEN)

Learning Fairness in Multi-Agent Systems

Jiechuan Jiang (Peking University) • Zongqing Lu (Peking University)

Primal-Dual Block Frank-Wolfe

Qi Lei (University of Texas at Austin) • JIACHENG ZHUO (University of Texas at Austin) • Constantine Caramanis (UT Austin) • Inderjit S Dhillon (UT Austin & Amazon) • Alexandros Dimakis (University of Texas, Austin)

GOT: An Optimal Transport framework for Graph comparison

Hermina Petric Maretic (Ecole Polytechnique Fédérale de Lausanne) • Mireille El Gheche (EPFL) • Giovanni Chierchia (ESIEE Paris) • Pascal Frossard (EPFL)

On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks

Sunil Thulasidasan (Los Alamos National Laboratory) • Gopinath Chennupati (Los Alamos National Laboratory) • Jeff Bilmes (University of Washington, Seattle) • Tanmoy Bhattacharya (Los Alamos National Laboratory) • Sarah Michalak (Los Alamos National Laboratory)

Complexity of Highly Parallel Non-Smooth Convex Optimization

Sebastien Bubeck (Microsoft Research) • Qijia Jiang (Stanford University) • Yin-Tat Lee () • Yuanzhi Li (Princeton) • Aaron Sidford (Stanford)

Inverting Deep Generative models, One layer at a time

Qi Lei (University of Texas at Austin) • Ajil Jalal (University of Texas at Austin) • Inderjit S Dhillon (UT Austin & Amazon) • Alexandros Dimakis (University of Texas, Austin)

Calculating Optimistic Likelihoods Using (Geodesically) Convex Optimization

Viet Anh Nguyen (EPFL) • Soroosh Shafieezadeh Abadeh (EPFL) • Man-Chung Yue (The Hong Kong Polytechnic University) • Daniel Kuhn (EPFL) • Wolfram Wiesemann (Imperial College)

The Implicit Metropolis-Hastings Algorithm

Kirill Neklyudov (Samsung AI Center, Moscow) • Evgenii Egorov (Skolkovo Institute of Science and Technology) • Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow)

An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints

Mehmet Fatih SAHIN (École polytechnique fédérale de Lausanne) • Armin eftekhari (EPFL) • Ahmet Alacaoglu (EPFL) • Fabian Latorre Gomez (EPFL) • Volkan Cevher (EPFL)

Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck

Maximilian Igl (University of Oxford) • Kamil Ciosek (Microsoft) • Yingzhen Li (Microsoft Research Cambridge) • Sebastian Tschiatschek (Microsoft Research) • Cheng Zhang (Microsoft) • Sam Devlin (Microsoft Research) • Katja Hofmann (Microsoft Research)

Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift

Jasper Snoek (Google Brain) • Yaniv Ovadia (Google Inc) • Emily Fertig (Google Brain) • Balaji Lakshminarayanan (Google DeepMind) • Sebastian Nowozin (Google Research) • D. Sculley (Google Research) • Joshua Dillon (Google) • Jie Ren (Google Inc.) • Zachary Nado (Google Inc.)

Accurate Layerwise Interpretable Competence Estimation

Vickram Rajendran (JHU Applied Physics Laboratory) • Will LeVine (Rice University)

A New Perspective on Pool-Based Active Classification and False-Discovery Control

Lalit Jain (University of Washington) • Kevin Jamieson (U Washington)

A First-Order Approach to Accelerated Value Iteration

Julien Grand Clement (IEOR Department, Columbia University) • Vineet Goyal (Columbia University)

Defending Neural Backdoors via Generative Distribution Modeling

Ximing Qiao (Duke University) • Yukun Yang (Duke University) • Hai Li (Duke University)

Are Sixteen Heads Really Better than One?

Paul Michel (Carnegie Mellon University, Language Technologies Institute) • Omer Levy (Facebook) • Graham Neubig (Carnegie Mellon University)

Multi-resolution Multi-task Gaussian Processes

Oliver Hamelijnck (The Alan Turing Institute) • Theodoros Damoulas (University of Warwick The Alan Turing Institute) • Kangrui Wang (The Alan Turing Institute) • Mark Girolami (Imperial College London)

Variational Bayesian Optimal Experimental Design

Adam Foster (University of Oxford) • Martin Jankowiak (Uber AI Labs) • Eli Bingham (Uber AI Labs) • Paul Horsfall (Uber AI Labs) • Yee Whye Teh (University of Oxford, DeepMind) • Tom Rainforth (University of Oxford) • Noah Goodman (Stanford University)

Universal Approximation of Input-Output Maps by Temporal Convolutional Nets

Joshua Hanson (University of Illinois) • Maxim Raginsky (University of Illinois at Urbana-Champaign)

Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes

Matt Jordan (UT Austin) • justin lewis (University of Texas at Austin) • Alexandros Dimakis (University of Texas, Austin)

Reinforcement Learning with Convex Constraints

Seyed Sobhan Mir Yoosefi (Princeton University) • Kianté Brantley (The University of Maryland College Park) • Hal Daume III (Microsoft Research & University of Maryland) • Miro Dudik (Microsoft Research) • Robert Schapire (MIcrosoft Research)

User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning

Dirk van der Hoeven (Leiden University)

Stochastic Bandits with Context Distributions

Johannes Kirschner (ETH Zurich) • Andreas Krause (ETH Zurich)

Inducing brain-relevant bias in natural language processing models

Dan Schwartz (Carnegie Mellon University) • Mariya Toneva (Carnegie Mellon University) • Leila Wehbe (Carnegie Mellon University)

Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning

Harm Van Seijen (Microsoft Research) • Mehdi Fatemi (Microsoft Research) • Arash Tavakoli (Imperial College London)

Recovering Bandits

Ciara Pike-Burke (Universitat Pompeu Fabra) • Steffen Grunewalder (Lancaster)

Computing Linear Restrictions of Neural Networks

Matthew Sotoudeh (University of California, Davis) • Aditya Thakur (University of California, Davis)

Learning Positive Functions with Pseudo Mirror Descent

Yingxiang Yang (University of Illinois at Urbana Champaign) • Haoxiang Wang (University of Illinois, Urbana-Champaign) • Negar Kiyavash (Georgia Institute of Technology) • Niao He (UIUC)

Correlation Priors for Reinforcement Learning

Bastian Alt (Technische Universität Darmstadt) • Adrian Šošić (Technische Universität Darmstadt) • Heinz Koeppl (Technische Universität Darmstadt)

Fast, Provably convergent IRLS Algorithm for p-norm Linear Regression

Deeksha Adil (University of Toronto) • Richard Peng (Georgia Tech / MSR Redmond) • Sushant Sachdeva (Yale University)

A Similarity-preserving Network Trained on Transformed Images Recapitulates Salient Features of the Fly Motion Detection Circuit

Yanis Bahroun (Flatiron institute) • Dmitri Chklovskii (Flatiron Institute, Simons Foundation) • Anirvan Sengupta (Rutgers University)

Differentially Private Covariance Estimation

Kareem Amin (Google Research) • Travis Dick (Carnegie Mellon University) • Alex Kulesza (Google) • Andres Munoz (Google) • Sergei Vassilvitskii (Google)

Outlier Detection and Robust PCA Using a Convex Measure of Innovation

Mostafa Rahmani (Baidu Research) • Ping Li (Baidu Research USA)

Integrating mechanistic and structural causal models enables counterfactual inference in complex systems

Robert Ness (Gamalon) • Kaushal Paneri (Northeastern University) • Olga Vitek (Northeastern University)

Are Disentangled Representations Helpful for Abstract Visual Reasoning?

Sjoerd van Steenkiste (The Swiss AI Lab - IDSIA) • Francesco Locatello (ETH Zürich - MPI Tübingen) • Jürgen Schmidhuber (Swiss AI Lab, IDSIA (USI & SUPSI) - NNAISENSE) • Olivier Bachem (Google Brain)

PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization

Thijs Vogels (EPFL) • Sai Praneeth Reddy Karimireddy (EPFL) • Martin Jaggi (EPFL)

Stochastic Frank-Wolfe for Composite Convex Minimization

Francesco Locatello (ETH Zürich - MPI Tübingen) • Alp Yurtsever (EPFL) • Olivier Fercoq (Telecom ParisTech) • Volkan Cevher (EPFL)

Consistent Constraint-Based Causal Structure Learning

Honghao Li (Institut Curie) • Vincent Cabeli (Institut Curie) • Nadir Sella (Institut Curie) • Herve Isambert (Institut Curie)

Unsupervised Discovery of Temporal Structure in Noisy Data with Dynamical Components Analysis

David Clark (Lawrence Berkeley National Laboratory) • Jesse Livezey (Lawrence Berkeley National Laboratory) • Kristofer Bouchard (Lawrence Berkeley National Laboratory)

Sample Efficient Active Learning of Causal Trees

Kristjan Greenewald (IBM Research) • Dmitriy Katz (IBM Research) • Karthikeyan Shanmugam (IBM Research, NY) • Sara Magliacane (IBM Research AI) • Murat Kocaoglu (MIT-IBM Watson AI Lab) • Enric Boix Adsera (MIT) • Guy Bresler (MIT)

Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection

Junran Peng (CASIA) • Ming Sun (sensetime.com) • ZHAO-XIANG ZHANG (Chinese Academy of Sciences, China) • Tieniu Tan (Chinese Academy of Sciences) • Junjie Yan (Sensetime Group Limited)

Robust Attribution Regularization

Jiefeng Chen (University of Wisconsin-Madison) • Xi Wu (Google) • Vaibhav Rastogi (University of Wisconsin-Madison) • Yingyu Liang (University of Wisconsin Madison) • Somesh Jha (University of Wisconsin, Madison)

Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization

Miika Aittala (MIT) • Prafull Sharma (MIT) • Lukas Murmann (Massachusetts Institute of Technology) • Adam Yedidia (Massachusetts Institute of Technology) • Gregory Wornell (MIT) • Bill Freeman (MIT/Google) • Fredo Durand (MIT)

When to use parametric models in reinforcement learning?

Hado van Hasselt (DeepMind) • Matteo Hessel (Google DeepMind) • John Aslanides (DeepMind)

General E(2)-Equivariant Steerable CNNs

Gabriele Cesa (University of Amsterdam) • Maurice Weiler (University of Amsterdam)

Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions

Murat Kocaoglu (MIT-IBM Watson AI Lab) • Karthikeyan Shanmugam (IBM Research, NY) • Amin Jaber (Purdue University) • Elias Bareinboim (Purdue)

Structure Learning with Side Information: Sample Complexity

Saurabh Sihag (Rensselaer Polytechnic Institute) • Ali Tajer (Rensselaer Polytechnic Institute)

Untangling in Invariant Speech Recognition

Cory Stephenson (Intel) • Jenelle Feather (MIT) • Suchismita Padhy (Intel AI Lab) • Oguz Elibol (Intel Nervana) • Hanlin Tang (Intel AI Products Group) • Josh McDermott (Massachusetts Institute of Technology) • Sueyeon Chung (MIT)

Flexible information routing in neural populations through stochastic comodulation

Caroline Haimerl (New York University) • Cristina Savin (NYU) • Eero Simoncelli (HHMI / New York University)

Generalization Bounds in the Predict-then-Optimize Framework

Othman El Balghiti (Columbia University) • Adam Elmachtoub (Columbia University) • Paul Grigas (UC Berkeley) • Ambuj Tewari (University of Michigan)

Categorized Bandits

Matthieu Jedor (ENS Paris-Saclay & Cdiscount) • Vianney Perchet (ENS Paris-Saclay & Criteo AI Lab) • Jonathan Louedec (Cdiscount)

Worst-Case Regret Bounds for Exploration via Randomized Value Functions

Daniel Russo (Columbia University)

Efficient characterization of electrically evoked responses for neural interfaces

Nishal Shah (Stanford University) • Sasidhar Madugula (Stanford University) • Pawel Hottowy (AGH University of Science and Technology in Kraków) • Alexander Sher (Santa Cruz Institute for Particle Physics, University of California, Santa Cruz) • Alan Litke (Santa Cruz Institute for Particle Physics, University of California, Santa Cruz) • Liam Paninski (Columbia University) • E.J. Chichilnisky (Stanford University)

Differentially Private Distributed Data Summarization under Covariate Shift

Kanthi K Sarpatwar (IBM T. J. Watson Research Center) • Karthikeyan Shanmugam (IBM Research, NY) • Venkata Sitaramagiridharganesh Ganapavarapu (IBM Research) • Ashish Jagmohan (IBM Research) • Roman Vaculin (IBM Research)

Hamiltonian descent for composite objectives

Brendan O'Donoghue (Google DeepMind) • Chris J. Maddison (Institute for Advanced Study, Princeton)

Implicit Regularization of Accelerated Methods in Hilbert Spaces

Nicolò Pagliana (Università degli studi di Genova (DIMA)) • Lorenzo Rosasco (University of Genova- MIT - IIT)

Non-Asymptotic Pure Exploration by Solving Games

Rémy Degenne (Centrum Wiskunde & Informatica, Amsterdam) • Wouter Koolen (Centrum Wiskunde & Informatica, Amsterdam) • Pierre Ménard (Institut de Mathématiques de Toulouse)

Implicit Posterior Variational Inference for Deep Gaussian Processes

Haibin YU (National University of Singapore) • Yizhou Chen (National University of Singapore) • Bryan Kian Hsiang Low (National University of Singapore) • Patrick Jaillet (MIT)

Deep Multi-State Dynamic Recurrent Neural Networks Operating on Wavelet Based Neural Features for Robust Brain Machine Interfaces

Benyamin Allahgholizadeh Haghi (California Institute of Technology) • Spencer Kellis (California Institute of Technology) • Sahil Shah (California Institute of Technology) • Maitreyi Ashok (California Institute of Technology) • Luke Bashford (California Institute of Technology) • Daniel Kramer (University of Southern California) • Brian Lee (University of Southern California) • Charles Liu (University of Southern California) • Richard Andersen (California Institute of Technology) • Azita Emami (California Institute of Technology)

Censored Semi-Bandits: A Framework for Resource Allocation with Censored Feedback

Arun Verma (IIT Bombay) • Manjesh K Hanawal (Indian Institute of Technology Bombay) • Arun Rajkumar (Xerox Research Center, India.) • Raman Sankaran (LinkedIn)

Cormorant: Covariant Molecular Neural Networks

Brandon Anderson (University of Chicago) • Truong Son Hy (The University of Chicago) • Risi Kondor (U. Chicago)

Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness

Andrey Malinin (University of Cambridge) • Mark Gales (University of Cambridge)

Reflection Separation using a Pair of Unpolarized and Polarized Images

Youwei Lyu (Beijing University of Posts and Telecommunications) • Zhaopeng Cui (ETH Zurich) • Si Li (Beijing University of Posts and Telecommunications) • Marc Pollefeys (ETH Zurich) • Boxin Shi (Peking University)

Policy Poisoning in Batch Reinforcement Learning and Control

Yuzhe Ma (University of Wisconsin-Madison) • Xuezhou Zhang (UW-Madison) • Wen Sun (Microsoft Research) • Jerry Zhu (University of Wisconsin-Madison)

Low-Complexity Nonparametric Bayesian Online Prediction with Universal Guarantees

Alix LHERITIER (Amadeus SAS) • Frederic Cazals (Inria)

Pure Exploration with Multiple Correct Answers

Rémy Degenne (Centrum Wiskunde & Informatica, Amsterdam) • Wouter Koolen (Centrum Wiskunde & Informatica, Amsterdam)

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets

Rohith Kuditipudi (Duke University) • Xiang Wang (Duke University) • HOLDEN LEE (Princeton) • Yi Zhang (Princeton) • Zhiyuan Li (Princeton University) • Wei Hu (Princeton University) • Rong Ge (Duke University) • Sanjeev Arora (Princeton University)

On the Benefits of Disentangled Representations

Francesco Locatello (ETH Zürich - MPI Tübingen) • Gabriele Abbati (University of Oxford) • Tom Rainforth (University of Oxford) • Stefan Bauer (MPI for Intelligent Systems) • Bernhard Schölkopf (MPI for Intelligent Systems) • Olivier Bachem (Google Brain)

Compiler Auto-Vectorization using Imitation Learning

Charith Mendis (MIT) • Cambridge Yang (MIT) • Yewen Pu (MIT) • Dr.Saman Amarasinghe (Massachusetts institute of technology) • Michael Carbin (MIT)

A Generalized Algorithm for Multi-Objective RL and Policy Adaptation

Runzhe Yang (Princeton University) • Xingyuan Sun (Princeton University) • Karthik Narasimhan (Princeton University)

Exact Gaussian Processes on a Million Data Points

Ke Wang (Cornell University) • Geoff Pleiss (Cornell University) • Jacob Gardner (Uber AI Labs) • Stephen Tyree (NVIDIA) • Kilian Weinberger (Cornell University) • Andrew Wilson (Cornell University)

Bayesian Layers: A Module for Neural Network Uncertainty

Dustin Tran (Google Brain) • Mike Dusenberry (Google Brain) • Mark van der Wilk (PROWLER.io) • Danijar Hafner (Google)

Learning Compositional Neural Programs with Recursive Tree Search and Planning

Thomas PIERROT (InstaDeep) • Guillaume Ligner (InstaDeep) • Scott Reed (Google DeepMind) • Olivier Sigaud (Sorbonne University) • Perrin Nicolas (ISIR) • David Kas (InstaDeep) • David Kas (InstaDeep) • Karim Beguir (InstaDeep) • Nando de Freitas (DeepMind)

Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric

Nirandika Wanigasekara (National University of Singapore) • Christina Lee Yu (Cornell University)

Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations

Debraj Basu (University of California Los Angeles) • Deepesh Data (UCLA) • Can Karakus (Amazon Web Services) • Suhas Diggavi (UCLA)

Likelihood Ratios for Out-of-Distribution Detection

Jie Ren (Google Brain) • Peter Liu (Google Brain) • Emily Fertig (Google Brain) • Jasper Snoek (Google Brain) • Ryan Poplin (Google) • Mark Depristo (Google) • Joshua Dillon (Google) • Balaji Lakshminarayanan (Google DeepMind)

Discrete Flows: Invertible Generative Models of Discrete Data

Dustin Tran (Google Brain) • Keyon Vafa (Columbia University) • Kumar Agrawal (Google AI Resident) • Laurent Dinh (Google Research) • Ben Poole (Google Brain)

Mindreader: A Self Validation Network for Object-Level Human Attention Reasoning

Zehua Zhang (Indiana University Bloomington) • Chen Yu (Indiana University) • David Crandall (Indiana University)

Model Selection for Contextual Bandits

Dylan Foster (MIT) • Akshay Krishnamurthy (Microsoft) • Haipeng Luo (University of Southern California)

Sliced Gromov-Wasserstein

Vayer Titouan (IRISA) • Rémi Flamary (Université Côte d'Azur, 3IA Côte d'Azur) • Nicolas Courty (IRISA, Universite Bretagne-Sud) • Romain Tavenard (LETG-Rennes / IRISA-Obelix) • Laetitia Chapel (IRISA)

Towards Practical Alternating Least-Squares for CCA

Zhiqiang Xu (Baidu Inc.) • Ping Li (Baidu Research USA)

Deep Leakage from Gradients

Ligeng Zhu (Simon Fraser University) • Zhijian Liu (MIT) • Song Han (MIT)

Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness

Fanny Yang (Stanford) • Zuowen Wang (ETH Zurich) • Christina Heinze-Deml (ETH Zurich)

Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks

Spencer Frei (UCLA) • Yuan Cao (UCLA) • Quanquan Gu (UCLA)

Value Function in Frequency Domain and Characteristic Value Iteration

Amir-massoud Farahmand (Vector Institute)

Icebreaker: Efficient Information Acquisition with Active Learning

Wenbo Gong (University of Cambridge) • Sebastian Tschiatschek (Microsoft Research) • Sebastian Nowozin (Microsoft Research Cambridge) • Richard E Turner (University of Cambridge) • José Miguel Hernández-Lobato (University of Cambridge) • Cheng Zhang (Microsoft)

Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors

Gauri Jagatap (Iowa State University) • Chinmay Hegde (Iowa State University)

Planning with Goal-Conditioned Policies

Soroush Nasiriany (University of California, Berkeley) • Vitchyr Pong (UC Berkeley) • Steven Lin (UC Berkeley) • Sergey Levine (UC Berkeley)

Don't take it lightly: Phasing optical random projections with unknown operators

Sidharth Gupta (University of Illinois at Urbana-Champaign) • Remi Gribonval (INRIA) • Laurent Daudet (LightOn) • Ivan Dokmanic (University of Illinois at Urbana-Champaign)

Generating Diverse High-Fidelity Images with VQVAE-2

Ali Razavi (DeepMind) • Aaron van den Oord (Google Deepmind) • Oriol Vinyals (Google DeepMind)

Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs

Pedro Mercado (University of Tübingen) • Francesco Tudisco (University of Strathclyde) • Matthias Hein (University of Tübingen)

Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis

Yingying Li (Harvard University) • Xin Chen (Harvard University) • Na Li (Harvard University)

Missing Not at Random in Matrix Completion: The Effectiveness of Estimating Missingness Probabilities Under a Low Nuclear Norm Assumption

Wei Ma (Carnegie Mellon University) • George Chen (Carnegie Mellon University)

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

Kundan Kumar (Universite de Montreal) • Rithesh Kumar (Mila) • Thibault de Boissiere (Lyrebird) • Lucas Gestin (Lyrebird) • Wei Zhen Teoh (Lyrebird) • Jose Sotelo (Lyrebird AI, MILA, Universite de Montreal) • Alexandre de Brébisson (LYREBIRD, MILA) • Yoshua Bengio (Mila) • Aaron Courville (U. Montreal)

Offline Contextual Bandits with High Probability Fairness Guarantees

Blossom Metevier (University of Massachusetts, Amherst) • Stephen Giguere (University of Massachusetts, Amherst) • Sarah Brockman (University of Massachusetts Amherst) • Ari Kobren (UMass Amherst) • Yuriy Brun (University of Massachusetts Amherst) • Emma Brunskill (Stanford University) • Philip Thomas (University of Massachusetts Amherst)

Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods

Maher Nouiehed (University of Southern California) • Maziar Sanjabi (USC) • Tianjian Huang (University of Southern California) • Jason Lee (USC) • Meisam Razaviyayn (University of Southern California)

Semantic-Guided Multi-Attention Localization for Zero-Shot Learning

Yizhe Zhu (Rutgers University ) • Jianwen Xie (Hikvision) • Zhiqiang Tang (Rutgers) • Xi Peng (University of Delaware) • Ahmed Elgammal (Rutgers University)

Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)

Mariya Toneva (Carnegie Mellon University) • Leila Wehbe (Carnegie Mellon University)

Function-Space Distributions over Kernels

Gregory Benton (Cornell University) • Wesley J Maddox (Cornell University) • Jayson Salkey (Cornell University) • Julio Albinati (Microsoft) • Andrew Wilson (Cornell University)

SGD for Least Squares Regression: Towards Minimax Optimality with the Final Iterate

Rong Ge (Duke University) • Sham Kakade (University of Washington) • Rahul Kidambi (University of Washington) • Praneeth Netrapalli (Microsoft Research)

Compositional Plan Vectors

Coline Devin (UC Berkeley) • Daniel Geng (UC Berkeley) • Pieter Abbeel (UC Berkeley Covariant) • Trevor Darrell (UC Berkeley) • Sergey Levine (UC Berkeley)

Locally Private Learning without Interaction Requires Separation

Amit Daniely (Google Research) • Vitaly Feldman (Google Brain)

Robust Bi-Tempered Logistic Loss Based on Bregman Divergences

Ehsan Amid (University of California, Santa Cruz) • Manfred Warmuth (Univ. of Calif. at Santa Cruz) • Rohan Anil (Google) • Tomer Koren (Google)

Computational Separations between Sampling and Optimization

Kunal Talwar (Google)

Surfing: Iterative Optimization Over Incrementally Trained Deep Networks

Ganlin Song (Yale University) • Zhou Fan (Yale Univ) • John Lafferty (Yale University)

Population-based Meta-Optimizer Guided by Posterior Estimation

Yue Cao (Texas A&M University) • Tianlong Chen (Texas A&M University) • Zhangyang Wang (TAMU) • Yang Shen (Texas A&M University)

On Human-Aligned Risk Minimization

Liu Leqi (Carnegie Mellon University) • Adarsh Prasad (Carnegie Mellon University) • Pradeep Ravikumar (Carnegie Mellon University)

Semi-Parametric Efficient Policy Learning with Continuous Actions

Victor Chernozhukov (MIT) • Mert Demirer (MIT) • Greg Lewis (Microsoft Research) • Vasilis Syrgkanis (Microsoft Research)

Multi-task Learning for Aggregated Data using Gaussian Processes

Fariba Yousefi (University of Sheffield) • Michael Smith (University of Sheffield) • Mauricio Álvarez (University of Sheffield)

Minimal Variance Sampling in Stochastic Gradient Boosting

Bulat Ibragimov (Yandex) • Gleb Gusev (Yandex)

Precise and Scalable Convex Relaxations for Robustness Certification

Gagandeep Singh (ETH Zurich) • Rupanshu Ganvir (ETH Zurich) • Markus Püschel (ETH Zurich) • Martin Vechev (DeepCode and ETH Zurich, Switzerland)

An Algorithm to Learn Polytree Networks with Hidden Nodes

Firoozeh Sepehr (University of Tennessee) • Donatello Materassi (University of Minnesota)

Efficiently Learning Fourier Sparse Set Functions

Andisheh Amrollahi (ETH Zurich) • Amir Zandieh (epfl) • Michael Kapralov (EPFL) • Andreas Krause (ETH Zurich)

Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions

Peng Chen (The University of Texas at Austin) • Keyi Wu (The University of Texas at Austin) • Joshua Chen (The University of Texas at Austin) • Tom O'Leary-Roseberry (The University of Texas at Austin) • Omar Ghattas (The University of Texas at Austin)

Invariance and identifiability issues for word embeddings

Rachel Carrington (University of Nottingham) • Karthik Bharath (University of Nottingham) • Simon Preston (University of Nottingham)

Generalization Error Analysis of Quantized Compressive Learning

Xiaoyun Li (Rutgers University) • Ping Li (Baidu Research USA)

Multi-Criteria Dimensionality Reduction with Applications to Fairness

Uthaipon Tantipongpipat (Georgia Tech) • Samira Samadi (Georgia Tech) • Mohit Singh (Georgia Tech) • Jamie Morgenstern (Georgia Tech) • Santosh Vempala (Georgia Tech)

Efficient Rematerialization for Deep Networks

Ravi Kumar (Google) • Manish Purohit (Google) • Zoya Svitkina (Google) • Erik Vee (Google) • Joshua Wang (Google)

Fast Agent Resetting in Training

Samuel Ainsworth (University of Washington) • Matt Barnes (University of Washington) • Siddhartha Srinivasa (Amazon + University of Washington)

Heterogeneous Treatment Effects with Instruments

Vasilis Syrgkanis (Microsoft Research) • Victor Lei (Trip Advisor) • Miruna Oprescu (Microsoft Research) • Maggie Hei (Microsoft) • Keith Battocchi (Microsoft) • Greg Lewis (Microsoft Research)

Understanding Sparse JL for Feature Hashing

Meena Jagadeesan (Harvard University)

Constraint Augmented Reinforcement Learning for Text-based Recommendation and Generation

Ruiyi Zhang (Duke University) • Tong Yu (Samsung Research America) • Yilin Shen (Samsung Research America) • Hongxia Jin (Samsung Research America) • Changyou Chen (University at Buffalo)

Flexible Modeling of Diversity with Strongly Log-Concave Distributions

Joshua Robinson (MIT) • Suvrit Sra (MIT) • Stefanie Jegelka (MIT)

Momentum-Based Variance Reduction in Non-Convex SGD

Ashok Cutkosky (Google Research) • Francesco Orabona (Boston University)

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning

Ben Eysenbach (Carnegie Mellon University) • Ruslan Salakhutdinov (Carnegie Mellon University) • Sergey Levine (UC Berkeley)

Can Unconditional Language Models Recover Arbitrary Sentences?

Nishant Subramani (New York University) • Samuel Bowman (New York University) • Kyunghyun Cho (NYU)

Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness

Xueru Zhang (University of Michigan) • Mohammad Mahdi Khalili (university of michigan) • Cem Tekin (Bilkent University) • mingyan liu (university of Michigan, Ann Arbor)

Faster width-dependent algorithm for mixed packing and covering LPs

Digvijay P Boob (Georgia Institute of Technology) • Saurabh Sawlani (Georgia Institute of Technology) • Di Wang (Georgia Institute of Technology)

Flattening a Hierarchical Clustering through Active Learning

Fabio Vitale (Sapienza University of Rome) • Anand Rajagopalan (Google) • Claudio Gentile (Google Research)

DeepWave: A Recurrent Neural-Network for Real-Time Acoustic Imaging

Matthieu SIMEONI (IBM/EPFL) • Sepand Kashani (EPFL) • Paul Hurley (Western Sydney University) • Martin Vetterli (EPFL)

Certifying Geometric Robustness of Neural Networks

Mislav Balunovic (ETH Zurich) • Maximilian Baader (ETH Zürich) • Gagandeep Singh (ETH Zurich) • Timon Gehr (ETH Zurich) • Martin Vechev (DeepCode and ETH Zurich, Switzerland)

Goal-conditioned Imitation Learning

Yiming Ding (University of California, Berkeley) • Carlos Florensa (UC Berkeley) • Pieter Abbeel (UC Berkeley Covariant) • Mariano Phielipp (Intel AI Labs)

Robust exploration in linear quadratic reinforcement learning

Jack Umenberger (Uppsala University) • Mina Ferizbegovic (KTH Royal Institute of Technology) • Thomas Schön (Uppsala University) • Håkan Hjalmarsson (KTH)

DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs

Ali Sadeghian (University of Florida) • Mohammadreza Armandpour (Texas A&M University) • Patrick Ding (Texas A&M University) • Daisy Zhe Wang (Univeresity of Florida)

Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration

Kwang-Sung Jun (Boston University) • Ashok Cutkosky (Google Research) • Francesco Orabona (Boston University)

Input-Output Equivalence of Unitary and Contractive RNNs

Melikasadat Emami (UCLA) • Mojtaba Sahraee Ardakan (UCLA) • Sundeep Rangan (NYU) • Alyson Fletcher (UCLA)

Hamiltonian Neural Networks

Samuel Greydanus (Google Brain) • Misko Dzumba (PetCube) • Jason Yosinski (Uber AI Labs)

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks

Qiyang Li (University of Toronto) • Saminul Haque (University of Toronto) • Cem Anil (University of Toronto; Vector Institute) • James Lucas (University of Toronto) • Roger Grosse (University of Toronto) • Joern-Henrik Jacobsen (Vector Institute)

Deep and Structured Similarity Matching via Deep and Structured Hebbian/Anti-Hebbian Networks

Dina Obeid (Harvard University) • Cengiz Pehlevan (Harvard University)

Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology

Nima Dehmamy (Northeastern University) • Albert-Laszlo Barabasi (Northeastern University) • Rose Yu (Northeastern University)

Multiple Futures Prediction

Charlie Tang (Apple Inc.) • Ruslan Salakhutdinov (Carnegie Mellon University)

Explicitly disentangling image content from translation and rotation with spatial-VAE

Tristan Bepler (MIT) • Ellen Zhong (Massachusetts Institute of Technology) • Kotaro Kelley (New York Structural Biology Center) • Edward Brignole (Massachusetts Institute of Technology) • Bonnie Berger (MIT)

A Perspective on False Discovery Rate Control via Knockoffs

Jingbo Liu (MIT) • Philippe Rigollet (MIT)

A Kernel Loss for Solving the Bellman Equation

Yihao Feng (The University of Texas at Austin) • Lihong Li (Google Brain) • Qiang Liu (UT Austin)

Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing

Jonas Mueller (Amazon Web Services) • Vasilis Syrgkanis (Microsoft Research) • Matt Taddy (Chicago Booth)

Differential Privacy Has Disparate Impact on Model Accuracy

Eugene Bagdasaryan (Cornell Tech, Cornell University) • Omid Poursaeed (Cornell University) • Vitaly Shmatikov (Cornell University)

Riemannian batch normalization for SPD neural networks

Daniel Brooks (Thales) • Olivier Schwander (Sorbonne Université) • Frederic Barbaresco (THALES LAND & AIR SYSTEMS) • Jean-Yves Schneider (THALES LAND & AIR SYSTEMS) • Matthieu Cord (Sorbonne University)

Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain Activity

Aria Wang (Carnegie Mellon University) • Leila Wehbe (Carnegie Mellon University) • Michael J Tarr (Carnegie Mellon University)

Stacked Capsule Autoencoders

Adam Kosiorek (University of Oxford) • Sara Sabour (Google) • Yee Whye Teh (University of Oxford, DeepMind) • Geoffrey E Hinton (Google & University of Toronto)

Learning Reward Machines for Partially Observable Reinforcement Learning

Rodrigo Toro Icarte (University of Toronto and Vector Institute) • Ethan Waldie (University of Toronto) • Toryn Klassen (University of Toronto) • Rick Valenzano (Element AI) • Margarita Castro (University of Toronto) • Sheila McIlraith (University of Toronto)

Learning Representations by Maximizing Mutual Information Across Views

Philip Bachman (Microsoft Research) • R Devon Hjelm (Microsoft Research) • William Buchwalter (Microsoft)

Learning Deep MRFs with Amortized Bethe Free Energy Minimization

Sam Wiseman (TTIC) • Yoon Kim (Harvard University)

Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity

Chulhee Yun (Massachusetts Institute of Technology) • Suvrit Sra (MIT) • Ali Jadbabaie (MIT)

Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks

Aaron Voelker (University of Waterloo) • Ivana Kajić (University of Waterloo) • Chris Eliasmith (U of Waterloo)

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

Maxime Gasse (Polytechnique Montréal) • Didier Chetelat (Polytechnique Montreal) • Nicola Ferroni (University of Bologna) • Laurent Charlin (MILA / U.Montreal) • Andrea Lodi (École Polytechnique Montréal)

Fast structure learning with modular regularization

Greg Ver Steeg (University of Southern California) • Hrayr Harutyunyan (USC Information Sciences Institute) • Daniel Moyer (USC Information Sciences Institute) • Aram Galstyan (USC Information Sciences Inst)

Wasserstein Dependency Measure for Representation Learning

Sherjil Ozair (Université de Montréal) • Corey Lynch (Google Brain) • Yoshua Bengio (Mila) • Aaron van den Oord (Google Deepmind) • Sergey Levine (UC Berkeley) • Pierre Sermanet (Google Brain)

TAB-VCR: Tags and Attributes for Visual Commonsense Reasoning

Jingxiang Lin (University of illinois at urbana-champaign) • Unnat Jain (UIUC) • Alexander Schwing (University of Illinois at Urbana-Champaign)

Universality and individuality in neural dynamics across large populations of recurrent networks

Niru Maheswaranathan (Google Brain) • Alex H Williams (Stanford University) • Matthew Golub (Stanford University) • Surya Ganguli (Stanford) • David Sussillo (Google Inc.)

End-to-End Learning on 3D Protein Structure for Interface Prediction

Raphael Townshend (Stanford University) • Patricia Suriana (Stanford) • Rishi Bedi (Stanford University) • Ron Dror (Stanford University)

A Family of Robust Stochastic Operators for Reinforcement Learning

Yingdong Lu (IBM Research) • Mark Squillante (IBM Research) • Chai Wah Wu (IBM)

Improving Model Robustness and Uncertainty Estimates with Self-Supervised Learning

Dan Hendrycks (UC Berkeley) • Mantas Mazeika (University of Chicago) • Saurav Kadavath (UC Berkeley) • Dawn Song (UC Berkeley)

Inherent Tradeoffs in Learning Fair Representation

Han Zhao (Carnegie Mellon University) • Geoff Gordon (Microsoft)

Are deep ResNets provably better than linear predictors?

Chulhee Yun (Massachusetts Institute of Technology) • Suvrit Sra (MIT) • Ali Jadbabaie (MIT)

Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics

Niru Maheswaranathan (Google Brain) • Alex H Williams (Stanford University) • Matthew Golub (Stanford University) • Surya Ganguli (Stanford) • David Sussillo (Google Inc.)

BehaveNet: nonlinear embedding and Bayesian neural decoding of behavioral videos

Eleanor Batty (Columbia University) • Matthew Whiteway (Columbia University) • Shreya Saxena (Columbia University) • Dan Biderman (Columbia University) • Taiga Abe (Columbia University) • Simon Musall (Cold Spring Harbor Laboratory) • Winthrop Gillis (Harvard Medical School) • Jeffrey Markowitz (Harvard Medical School) • Anne Churchland (Cold Spring Harbor Laboratory) • John Cunningham (University of Columbia) • Sandeep R Datta (Harvard Medical School) • Scott Linderman (Stanford University) • Liam Paninski (Columbia University)

Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models

Yuge Shi (University of Oxford) • Siddharth Narayanaswamy (Unversity of Oxford) • Brooks Paige (Alan Turing Institute) • Philip Torr (University of Oxford)

Gradient-based Adaptive Markov Chain Monte Carlo

Michalis Titsias (DeepMind) • Petros Dellaportas (University College London, Athens University of Economics and Alan Turing Institute)

On the Role of Inductive Bias From Simulation and the Transfer to the Real World: a new Disentanglement Dataset

Muhammad Waleed Gondal (Max Planck Institute for Intelligent Systems) • Manuel Wuthrich (Max Planck Institute for Intelligent Systems) • Djordje Miladinovic (ETH Zurich) • Francesco Locatello (ETH Zürich - MPI Tübingen) • Martin Breidt (MPI for Biological Cybernetics) • Valentin Volchkov (Max Planck Institut for Intelligent Systems) • Joel Akpo (Max Planck Institute for Intelligent Systems) • Olivier Bachem (Google Brain) • Bernhard Schölkopf (MPI for Intelligent Systems) • Stefan Bauer (MPI for Intelligent Systems)

Imitation-Projected Policy Gradient for Programmatic Reinforcement Learning

Abhinav Verma (Rice University) • Hoang Le (California Institute of Technology) • Yisong Yue (Caltech) • Swarat Chaudhuri (Rice University)

Learning Data Manipulation for Augmentation and Weighting

Zhiting Hu (Carnegie Mellon University) • Bowen Tan (CMU) • Ruslan Salakhutdinov (Carnegie Mellon University) • Tom Mitchell (Carnegie Mellon University) • Eric Xing (Petuum Inc. / Carnegie Mellon University)

Exploring Algorithmic Fairness in Robust Graph Covering Problems

Aida Rahmattalabi (University of Southern California) • Phebe Vayanos (University of Southern California) • Anthony Fulginiti (University of Denver) • Eric Rice (University of Southern California) • Bryan Wilder () • Amulya Yadav (Pennsylvania State University) • Milind Tambe (USC)

Abstraction based Output Range Analysis for Neural Networks

Pavithra Prabhakar (Kansas State University) • Zahra Rahimi Afzal (Kansas State University)

Space and Time Efficient Kernel Density Estimation in High Dimensions

Arturs Backurs (MIT) • Piotr Indyk (MIT) • Tal Wagner (MIT)

PIDForest: Anomaly Detection and Certification via Partial Identification

Parikshit Gopalan (VMware Research) • Vatsal Sharan (Stanford University) • Udi Wieder (VMware Research)

Generative Models for Graph-Based Protein Design

John Ingraham (MIT) • Vikas Garg (MIT) • Regina Barzilay (Massachusetts Institute of Technology) • Tommi Jaakkola (MIT)

The Geometry of Deep Networks: Power Diagram Subdivision

Randall Balestriero (Ecole Normale Superieure, Paris) • Romain Cosentino (Rice University) • Behnaam Aazhang (Rice University) • Richard Baraniuk (Rice University)

Approximate Feature Collisions in Neural Nets

Ke Li (UC Berkeley) • Tianhao Zhang (Nanjing University) • Jitendra Malik (University of California at Berkley)

Ease-of-Teaching and Language Structure from Emergent Communication

Fushan Li (University of Alberta) • Michael Bowling (University of Alberta)

Generalization in multitask deep neural classifiers: a statistical physics approach

Anthony Ndirango (Intel AI Lab) • Tyler Lee (Intel AI Lab)

Distributionally Optimistic Optimization Approach to Nonparametric Likelihood Approximation

Viet Anh Nguyen (EPFL) • Soroosh Shafieezadeh Abadeh (EPFL) • Man-Chung Yue (The Hong Kong Polytechnic University) • Daniel Kuhn (EPFL) • Wolfram Wiesemann (Imperial College)

On Relating Explanations and Adversarial Examples

Alexey Ignatiev (Reason Lab, Faculty of Sciences, University of Lisbon) • Nina Narodytska (VMWare Research) • Joao Marques-Silva (Reason Lab, Faculty of Sciences, University of Lisbon)

On the equivalence between graph isomorphism testing and function approximation with GNNs

Zhengdao Chen (New York University) • Soledad Villar (New York University) • Lei Chen (New York University) • Joan Bruna (NYU)

Surround Modulation: A Bio-inspired Connectivity Structure for Convolutional Neural Networks

Hosein Hasani (Sharif University of Technology) • Mahdieh Soleymani (Sharif University of Technology) • Hamid Aghajan (Sharif University of Technology and iMinds, Gent University,)

Self-attention with Functional Time Representation Learning

Da Xu (Walmart Labs) • Chuanwei Ruan (Walmart Labs) • Evren Korpeoglu (Walmart Labs) • Sushant Kumar (Walmart Labs) • Kannan Achan (Walmart Labs)

Re-randomized Densification for One Permutation Hashing and Bin-wise Consistent Weighted Sampling

Ping Li (Baidu Research USA) • xiaoyun Li (Rutgers) • Cun-Hui Zhang (Rutgers)

Enabling hyperparameter optimization in sequential autoencoders for spiking neural data

Mohammad Reza Keshtkaran (Emory University and Georgia Tech) • Chethan Pandarinath (Emory University and Georgia Tech)

Sophia-11/Awesome-NeurIPS2019-NIPS2019

Sophia-11

Reviews

Repository Details

Awesome-NeurIPS2019-NIPS

本内容现在是NIPS2019,后期会随时更新为

Awesome-NIPS2019 陆续更新录用论文

论文下载百度云链接：链接：https://pan.baidu.com/s/100OAXTIOTPoMjbi-dwOcxA

Update log

Table of Contents

全部

More Repositories