QMCTorch

Use and design neural network ansatz wave function for real-space quantum Monte Carlo simulations of molecular systems.

2
contributors

Cite this software

DOI:
[[ releases.length > 0 ? releases[selectedIndex].doi : conceptDOI ]]
Copy to clipboard
Choose a reference manager file format:
Download file

What QMCTorch can do for you

  • Easily use and implement new neural network ansatz
  • Use ADF or pySCF as SCF backend
  • Use Horovod to deploy on GPU clusters

In QMCTorch the trial wave function is calculated by a small, physically motivated network. Starting from the electronic positions, R, the first layer computes the values of all atomic orbitals for all electrons. From there a linear map computes the values of all relevant molecular orbitals. A Slater Pooling mask is then applied to compute all Slater determinants that are finally combined by a fully connected layer. The Jastrow factors are computed in parallel and combined with the CI expansion to obtain the value of the wave function

Read more
Tags
  • High performance computing
  • GPU
  • Machine learning
Programming Language
  • Python
License
  • Apache-2.0

Participating organizations

Contributors

  • Nicolas Renaud
    Netherlands eScience Center
  • Felipe Zapata
    Netherlands eScience Center
Contact person
Nicolas Renaud
Netherlands eScience Center

Information for page maintainers

OAI-PMH metadata:
Expected a redirect from a conceptdoi to a versioned doi, got 200 instead.
citation metadata:
doi is not a concept doi.
Show