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

A curated list of awesome Deep Learning tutorials, projects and communities.

A Dataset for Direct Quotation Extraction and Attribution in News Articles.

Code for KHGT model, AAAI2021

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).

A Python package to process & model ChEMBL data.

Implementation of "StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis"

Fully convolutional networks for semantic segmentation

Compare neural networks by their feature similarity

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Understanding the Effects of Datasets Characteristics on Offline Reinforcement Learning

[CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation

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

The codes and related files to reproduce the results for Image Similarity Challenge Track 1.

Allows including an action inside another action (by preprocessing the Yaml file). This is how composite actions should have worked.

Hierarchical Clustering: O(1)-Approximation for Well-Clustered Graphs

MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks

Implement Decoupled Neural Interfaces using Synthetic Gradients in Pytorch

PyTorch implementation of paper A Fast Knowledge Distillation Framework for Visual Recognition.

Use tensorflow to implement a Deep Neural Network for real time lane detection