Skip to content

Surrogate natural gradient descent (SNGD) experiments.

Notifications You must be signed in to change notification settings

cambridge-mlg/sngd

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

sngd

Code to accompany the paper "Optimising Distributions with Natural Gradient Surrogates".

NB: we have only included synthetic datasets in this repository; details of the datasets used in the paper can be found in Appendix D.

Example usage:

pip install -e .
python -m experiments.mvsn_ml sngd --dataset=synthetic --lr-theta=1e-2 --lr-lam=1e-2

About

Surrogate natural gradient descent (SNGD) experiments.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages