Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
Apr 4, 2019
Apr 2, 2019
Apr 4, 2019
Apr 2, 2019
Jun 10, 2019

Functional Variational Bayesian Neural Networks

This code is jointly contributed by Shengyang Sun, Guodong Zhang and Jiaxin Shi.

Introduction

Code for "Functional variational Bayesian neural networks" (https://arxiv.org/abs/1903.05779)

Dependencies

This project runs with Python 3.6. Before running the code, you have to install

Experiments

Periodic Prior RBF Prior

Below we shows some examples to run the experiments.

x3 regression

python exp/toy.py -d x3 -in 0.01

sinusoidal extrapolation

python exp/toy.py -d sin -na 40 -nh 5 -nu 500 -e 50000 -il -2

Inference on Implicit Piecewise Priors

python exp/piecewise.py -d p_const

Regression

python exp/regression.py -d yacht

Contextual Bandits

python exp/bandits.py --data_type statlog

Citation

To cite this work, please use

@article{sun2019functional,
  title={Functional Variational Bayesian Neural Networks},
  author={Sun, Shengyang and Zhang, Guodong and Shi, Jiaxin and Grosse, Roger},
  journal={arXiv preprint arXiv:1903.05779},
  year={2019}
}

About

Code for "Functional variational Bayesian neural networks" (https://arxiv.org/abs/1903.05779)

Topics

Resources

Releases

No releases published

Packages

No packages published

Languages