DeepQMC 1.1.2

Added

• Add script to run common configs before release

Changed

• Change location of hydra output dir
• Extend development workflow with codespell and mypy
• Update workflows
• Add pre-commit hooks
• Extend documentation
• Run tests in double precision

DeepQMC 1.1.1

Changed

• Refactor and code cleanup
• Refactor parallel utils for more efficient pmaps

Fixed

• Errors when executing tutorial
• Ansatz config files
• Tensorboard logging
• Bug crashing energy evaluation
• Saving of final checkpoint

DeepQMC 1.1.0

Changed

• Refactor and simplify the PauliNet
• Generalize the GNN framework
• Remove wave function state and cutoff mechanism
• Remove defaults from code and fully transition to ansatz initialization through hydra
• Implement pseudo potentials
• Implement training on multiple molecular configurations (undocumented)
• Add configuration files for PauliNet, FermiNet, DeepErwin and PsiFormer
• Add multi-GPU support

Fixed

• Remove deepcopys slowing down the execution
• Improve logging
• Explicit creation of logging directories

Removed

• Remove specification of orbital configurations in wave function ansatz
• Remove GraphNeuralNetwork base class

Renamed

• PauliNet -> NeuralNetworkWaveFunction
• SchNet -> ElectronGNN

DeepQMC 1.0.1

Fixed

• Issues related to sampler initialization and synchronization with parameter update
• Minor issues with logging, rewinding and checkpointing mechanisms
• Improve compatibility of cli and slurm

DeepQMC 1.0.0

This release reimplements the DeepQMC package in jax. This involves significant changes to the code as well as the API.

DeepQMC 0.3.1

Fixed

• Version incompatibility of PySCF and H5PY
• Minor issues with walker initialization in some systems
• Minor numerical instability causing rare NaNs

DeepQMC 0.3.0

Added

• PauliNet:
  • Mean-field Jastrow and backflow
• H2O and H4 rectangle systems
• Support for Python 3.9

Changed

• PauliNet/OmniSchNet:
  • API

Removed

• PauliNet:
  • Separate Jastrow and backflow factories
  • mo_factory, functionality replaced with a mean-field backflow
  • Real-space backflow

Fixed

• Systems with n_up/n_down = 0

DeepQMC 0.2.0

Added

• Command-line interface

Changed

• PauliNet:
  • Nuclear and electronic cusp corrections on by default
  • omni_kwargs accepted by PauliNet() instead of from_hf()
  • All keyword arguments to from_hf() are passed to PauliNet()
• Sampler:
  • from_mf() changed to from_wf(), doesn't use PySCF object by default

DeepQMC 0.1.1

Rerelease of 0.1.0 with added package metadata.

DeepQMC 0.1.0

This is the first official release of DeepQMC.

At this moment, DeepQMC should be still considered a research code.

Added

• Core functionality to run variational quantum Monte Carlo with Pytorch
• PauliNet, a deep neural network ansatz