Discover p-lambda/robust_tradeoff Open Source project

Stars
8
Rank 2,087,750 (Top 42 %)
Language
Python
License
MIT License
Created about 4 years ago
Updated over 3 years ago

p-lambda

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Code for the ICML 2020 paper "Understanding and Mitigating the Tradeoff Between Robustness and Accuracy", Aditi Raghunathan, Sang Michael Xie, Fanny Yang, John Duchi, and Percy Liang. Paper available at https://arxiv.org/pdf/2002.10716.pdf.

wilds

A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.

Python

545

dsir

DSIR large-scale data selection framework for language model training

Python

199

jukemir

Perform transfer learning for MIR using Jukebox!

Shell

171

verified_calibration

Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlight).

Python

137

incontext-learning

Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implicit Bayesian Inference"

Python

gradual_domain_adaptation

Python

swords

The Stanford Word Substitution (Swords) Benchmark

Python

in-n-out

Code for the ICLR 2021 Paper "In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness"

Python

composed_finetuning

Code for the ICML 2021 paper "Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization" by Sang Michael Xie, Tengyu Ma, Percy Liang

Python

p-lambda/robust_tradeoff

p-lambda

Reviews

Repository Details

More Repositories