Differentiable Annealed Importance Sampling (DAIS)

This repository contains the code to reproduce the DAIS results from the paper Differentiable Annealed Importance Sampling and the Perils of Gradient Noise.

Bayesian Linear Regression

Please first install JAX (https://github.com/google/jax), then reproduce our results by running the following:

python blr/dais.py --gamma 0.0
python blr/dais.py --gamma 0.9
python blr.dais.py --bsize 100

Variational Autoencoder

Please first install PyTorch (https://pytorch.org/).

For training, one example command for DAIS with $K = 10$ and $S = 5$ (to adapt annealing scheme, add --adapt_beta):

python vae/mnist_train.py --lf_step 10 --n_particles 5 --lf_lrate 0.08

After training, you can find the saved checkpoint and evaluate it (e.g., using AIS):

python vae/mnist_eval.py --ais --n_particles 10 --lf_step 10000 --lf_lrate 0.05 --resume xxx

Also, you can reproduce the evaulation results of AIS/HAIS/DAIS by runing vae/mnist_eval_scaling.py:

python vae/mnist_eval_scaling.py --linear_beta --lf_lrate 0.08 --n_particles 10 --resume xxx

Citation

To cite this work, please use

@inproceedings{
	zhang2021differentiable,
	title={Differentiable Annealed Importance Sampling and the Perils of Gradient Noise},
	author={Guodong Zhang and Kyle Hsu and Jianing Li and Chelsea Finn and Roger Baker Grosse},
	booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},
	year={2021},
	url={https://openreview.net/forum?id=6rqjgrL7Lq}
}

Differentiable Annealed Importance Sampling (DAIS)

Related tags

Overview

Differentiable Annealed Importance Sampling (DAIS)

Bayesian Linear Regression

Variational Autoencoder

Citation

Owner

Guodong Zhang

Shuffle Attention for MobileNetV3

UFPR-ADMR-v2 Dataset

Benchmark for Answering Existential First Order Queries with Single Free Variable

Contrastive Learning for Metagenomic Binning

Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.

G-NIA model from "Single Node Injection Attack against Graph Neural Networks" (CIKM 2021)

pytorch bert intent classification and slot filling

Sparse-dense operators implementation for Paddle

Vehicle direction identification consists of three module detection , tracking and direction recognization.

Algorithmic Trading using RNN

This repository contains the entire code for our work "Two-Timescale End-to-End Learning for Channel Acquisition and Hybrid Precoding"

A Strong Baseline for Image Semantic Segmentation

This is the open-source reference implementation of the SIGGRAPH 2021 paper Intersection-free Rigid Body Dynamics.

Try out deep learning models online on Google Colab

Code for Environment Inference for Invariant Learning (ICML 2020 UDL Workshop Paper)

Implementation of character based convolutional neural network

Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition

Unofficial Tensorflow 2 implementation of the paper Implicit Neural Representations with Periodic Activation Functions

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.