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

This repository contains code released by Google Research.

Using pytorch to implement unet network for liver image segmentation.

LIMEcraft: Handcrafted superpixel selectionand inspection for Visual eXplanations

Official code repository for "Exploring Neural Models for Query-Focused Summarization"

Node Dependent Local Smoothing for Scalable Graph Learning

Maximum Spatial Perturbation for Image-to-Image Translation (Official Implementation)

CLIP (Contrastive Language–Image Pre-training) trained on Indonesian data

[ICCV 2021] Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation

Distributing reference energies for SMIRNOFF implementations

An example of time series augmentation methods with Keras

PyTorch implementation of MICCAI 2018 paper "Liver Lesion Detection from Weakly-labeled Multi-phase CT Volumes with a Grouped Single Shot MultiBox Detector"

DualGAN-tensorflow: tensorflow implementation of DualGAN

BiSeNet based on pytorch

Analyses of the individual electric field magnitudes with Roast.

Group Fisher Pruning for Practical Network Compression(ICML2021)

Pytorch implementation of DeePSiM

Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features"

MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;

Hierarchical Few-Shot Generative Models

PyTorch implementation of Advantage async actor-critic Algorithms (A3C) in PyTorch