Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implement calculations in periodic boundary conditions #49

Merged
merged 6 commits into from Jul 12, 2022
Merged

Conversation

gcassella
Copy link
Contributor

Includes the feature layer, envelope, and Hamiltonian described in

Cassella, G., Sutterud, H., Azadi, S., Drummond, N.D., Pfau, D.,
Spencer, J.S. and Foulkes, W.M.C., 2022. Discovering Quantum Phase Transitions
with Fermionic Neural Networks. arXiv preprint arXiv:2202.05183.

Several changes to the configuration interface for feature layers and envelopes have been made. These are now specified by an interface similar to the local energy function. These changes, and the new periodic boundary conditions, are demonstrated in ferminet.configs.heg.

Other miscellaneous changes:

  • Reduced failure threshold for the pylint step of the GitHub CI workflow to 9.75/10.0. This prevents the CI from failing over linting errors that are acceptable under the in-house style.
  • Implemented dummy element 'X' with atomic number zero. Used to define the coordinate system for one-electron features in systems without nuclei (e.g. the homogeneous electron gas).

Includes the feature layer, envelope, and Hamiltonian described in
```Cassella, G., Sutterud, H., Azadi, S., Drummond, N.D., Pfau, D.,
Spencer, J.S. and Foulkes, W.M.C., 2022. Discovering Quantum Phase Transitions
with Fermionic Neural Networks. arXiv preprint arXiv:2202.05183.```

Several changes to the configuration interface for feature layers and envelopes have been made. These are now specified by an interface similar to the local energy function. These changes, and the new periodic boundary conditions, are demonstrated in `ferminet.configs.heg`.
@gcassella gcassella marked this pull request as ready for review June 29, 2022 12:07
@jsspencer jsspencer self-requested a review June 29, 2022 12:22
@jsspencer jsspencer self-assigned this Jun 30, 2022
Copy link
Collaborator

@jsspencer jsspencer left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is awesome, thank you!

ferminet/configs/heg.py Show resolved Hide resolved
ferminet/configs/heg.py Outdated Show resolved Hide resolved
ferminet/configs/heg.py Outdated Show resolved Hide resolved
ferminet/configs/heg.py Outdated Show resolved Hide resolved
ferminet/pbc/envelopes.py Outdated Show resolved Hide resolved
ferminet/tests/networks_test.py Outdated Show resolved Hide resolved
ferminet/train.py Outdated Show resolved Hide resolved
ferminet/train.py Outdated Show resolved Hide resolved
ferminet/pbc/hamiltonian.py Outdated Show resolved Hide resolved
ferminet/pbc/hamiltonian.py Outdated Show resolved Hide resolved
@gcassella
Copy link
Contributor Author

I think that addresses all of the comments - thank you for taking the time to go through everything and make clear recommendations 😄

@copybara-service copybara-service bot merged commit 41351a2 into google-deepmind:main Jul 12, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants