Skip to content

Latest commit

 

History

History
 
 

cold_posterior_flax

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
cifar10
cifar10
 
 
README.md
README.md
 
 

README.md

Flax implementation of Cold Posterior experiments.

This repository contains Flax implementations of the SG-MCMC experiments from the paper How Good is the Bayes Posterior in Deep Neural Networks Really?. It is based on the pre-linen Flax API.

Please see the README files in the subdirectories for more information.

Current Status

NOTE: This implementation is work in progress!

For questions reach out to

Bas Veeling (basveeling@gmail.com)
Tim Salimans (salimans@google.com)

Reference

Florian Wenzel, Kevin Roth, Bastiaan S. Veeling, Jakub Swiatkowski, Linh Tran, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton and Sebastian Nowozin (2020). How Good is the Bayes Posterior in Deep Neural Networks Really?. In International Conference of Machine Learning.