wiseodd/wiseodd.github.io

Stars
39
Rank 693,563 (Top 14 %)
Language MDX
License
MIT License
Created almost 9 years ago
Updated 2 months ago

wiseodd/wiseodd.github.io

wiseodd

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

Agustinus‘ personal website and blog

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

MCMC

Collection of Monte Carlo (MC) and Markov Chain Monte Carlo (MCMC) algorithms applied on simple examples.

hipsternet

All the hipster things in Neural Net in a single repo

controlled-text-generation

Reproducing Hu, et. al., ICML 2017's "Toward Controlled Generation of Text"

probabilistic-models

Collection of probabilistic models and inference algorithms

natural-gradients

Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)

last_layer_laplace

Last-layer Laplace approximation code examples

Jupyter Notebook

cnn-levelset

Source code for Kristiadi and Pranowo, 2017's "Deep Convolutional Level Set Method for Image Segmentation"

pub-ready-plots

Agustinus' very opiniated publication-ready plotting library

lula

Companion code for the paper "Learnable Uncertainty under Laplace Approximations" (UAI 2021).

compound-density-networks

Implementation of: Kristiadi, Agustinus, and Asja Fischer. "Predictive Uncertainty Quantification with Compound Density Networks." (2019).

lapeft-bayesopt

Discrete Bayesian optimization with LLMs, PEFT finetuning methods, and the Laplace approximation.

cuda-pso

Comparison between CUDA and CPU for PSO using 3-dimensional Levy function as test case

bayesian_ood_training

Jupyter Notebook

swarm-image-segmenter

Image segmentation using swarm intelligence, accelerated using GPGPU (CUDA)

laplace-bayesopt

Laplace approximated BNN surrogate for BoTorch

phd_thesis_template

rgpr

Companion code for the paper "An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence" (NeurIPS 2021)

two-funds-rebalancer

Given your current portfolio value, desired allocation after rebalancing, and the amount of cash you have, this script will output how much of your cash should be used to buy stock/bonds (in percent). Only works for portfolios with two funds, e.g. the Couch Potato and classic two-funds 60-40 portfolios.

llm-bayesopt-exps

Official experiment code for the "Sober Look at LLMs for Material Discovery" paper.

bo-async-feedback