Name		Name	Last commit message	Last commit date
parent directory ..
tests		tests
README.md		README.md
__init__.py		__init__.py
curvature_blocks.py		curvature_blocks.py
distributions.py		distributions.py
estimator.py		estimator.py
example.py		example.py
layers_and_loss_tags.py		layers_and_loss_tags.py
loss_functions.py		loss_functions.py
optimizer.py		optimizer.py
requirements.txt		requirements.txt
run.sh		run.sh
setup.py		setup.py
tag_graph_matcher.py		tag_graph_matcher.py
tracer.py		tracer.py
utils.py		utils.py

README.md

Accompanying code for Better, Faster Fermionic Neural Networks

All package requirements are listed in requirements.txt.

Contributing

This is purely research code, provided with no further intentions of support or any guarantees of backward compatibility.

Installation

git clone [email protected]:deepmind/deepmind-research.git
pip install deepmind_research/kfac_ferminet_alpha/

Usage

You can find examples of how to use the codebase through the FermiNet project.

We also provide an example training script.

Reference

Better, Faster Fermionic Neural Networks

James S. Spencer, David Pfau, Aleksandar Botev, and W. M. C. Foulkes.

URL: https://arxiv.org/abs/2011.07125.

Optimizing Neural Networks with Kronecker-factored Approximate Curvature

James Martens, Roger Grosse

URL: https://arxiv.org/abs/1503.05671