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

用强化学习DQN算法，训练AI模型来玩合成大西瓜游戏，提供Keras版本和PARL（paddle）版本

A `Neural = Symbolic` framework for sound and complete weighted real-value logic

Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

Implementation of PersonaGPT Dialog Model

Code for all the Advent of Code'21 challenges mostly written in python

Only valid pull requests will be allowed. Use python only and readme changes will not be accepted.

Official Implementation of Swapping Autoencoder for Deep Image Manipulation (NeurIPS 2020)

(CVPR 2021) Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

SAMO: Streaming Architecture Mapping Optimisation

Code repo for "Towards Interpretable Deep Networks for Monocular Depth Estimation" paper.

Code release for DS-NeRF (Depth-supervised Neural Radiance Fields)

Generate indoor scenes with Transformers

Official PyTorch Implementation for InfoSwap: Information Bottleneck Disentanglement for Identity Swapping

Part-aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking

Reinforcement Learning via Supervised Learning

Discriminative Condition-Aware PLDA

Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition - NeurIPS2021

Dataloader tools for language modelling

Fake videos detection by tracing the source using video hashing retrieval.

RGB-D Local Implicit Function for Depth Completion of Transparent Objects