EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DeepQMC: An open-source software suite for variational optimization of deep-learning molecular wave functions

Z Schätzle iD, P B Szabó iD, M Mezera iD, J Hermann iD, F Noé iD

The Journal of Chemical Physics · 07.09.2023 · 159 (9)

DOI: 10.1063/5.0157512 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 06.09.2023. Verfasst von Z Schätzle und 4 weiteren Autor:innen. Beteiligte Einrichtung: FU Berlin, Department of Mathematics and Computer Science, Arnimallee 6, Berlin 14195, Germany. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020 Framework Program, Berlin Mathematics Research Center MATH+.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computing accurate yet efficient approximations to the solutions of the electronic Schrödinger equation has been a paramount challenge of computational chemistry for decades. Quantum Monte Carlo methods are a promising avenue of development as their core algorithm exhibits a number of favorable properties: it is highly parallel and scales favorably with the considered system size, with an accuracy that is limited only by the choice of the wave function Ansatz. The recently introduced machine-learned parametrizations of quantum Monte Carlo Ansätze rely on the efficiency of neural networks as universal function approximators to achieve state of the art accuracy on a variety of molecular systems. With interest in the field growing rapidly, there is a clear need for easy to use, modular, and extendable software libraries facilitating the development and adoption of this new class of methods. In this contribution, the DeepQMC program package is introduced, in an attempt to provide a common framework for future investigations by unifying many of the currently available deep-learning quantum Monte Carlo architectures. Furthermore, the manuscript provides a brief introduction to the methodology of variational quantum Monte Carlo in real space, highlights some technical challenges of optimizing neural network wave functions, and presents example black-box applications of the program package. We thereby intend to make this novel field accessible to a broader class of practitioners from both the quantum chemistry and the machine learning communities.

Autor:innen und Institutionen

  • FU Berlin, Department of Mathematics and Computer Science, Arnimallee 6, Berlin 14195, Germany.
  • Microsoft Research AI4Science, Karl-Liebknecht Str. 32, Berlin 10178, Germany.
  • FU Berlin, Department of Physics, Arnimallee 14, Berlin 14195, Germany.
  • Rice University, Department of Chemistry, Houston, Texas 77005, USA.

ORCID-Profile: Z Schätzle, P B Szabó, M Mezera, J Hermann, F Noé

Förderung

  • Horizon 2020 Framework Program
  • Berlin Mathematics Research Center MATH+

Zitieren

APA

Schätzle, Z., Szabó, P. B., Mezera, M., Hermann, J., & Noé, F. (2023). DeepQMC: An open-source software suite for variational optimization of deep-learning molecular wave functions. The Journal of Chemical Physics, 159(9). https://doi.org/10.1063/5.0157512

Vancouver

Schätzle Z, Szabó PB, Mezera M, Hermann J, Noé F. DeepQMC: An open-source software suite for variational optimization of deep-learning molecular wave functions. The Journal of Chemical Physics. 2023;159(9). doi:10.1063/5.0157512

BibTeX
@article{Schtzle2023,
  author = {Schätzle, Z and Szabó, P B and Mezera, M and Hermann, J and Noé, F},
  title = {DeepQMC: An open-source software suite for variational optimization of deep-learning molecular wave functions},
  journal = {The Journal of Chemical Physics},
  year = {2023},
  volume = {159},
  number = {9},
  doi = {10.1063/5.0157512}
}
Kostenlos starten →