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

Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network.

Localizing Visual Sounds the Hard Way

The-Secret-Sharing-Schemes - This interactive script demonstrates the Secret Sharing Schemes algorithm

An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

ICON: Implicit Clothed humans Obtained from Normals

Cookiecutter PyTorch Lightning

My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot

Space robot - (Course Project) Using the space robot to capture the target satellite that is disabled and spinning, then stabilize and fix it up

(IEEE TIP 2021) Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"

Implementation of the paper Scalable Intervention Target Estimation in Linear Models (NeurIPS 2021), and the code to generate simulation results.

Train the HRNet model on ImageNet

Understanding Hyperdimensional Computing for Parallel Single-Pass Learning

Angora is a mutation-based fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without symbolic execution.

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.

MAVE: : A Product Dataset for Multi-source Attribute Value Extraction

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

Deep learned, hardware-accelerated 3D object pose estimation

Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation

Code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" (CVPR 2020)