IRUS Total

Ab-initio solution of the many-electron Schrödinger equation with deep neural networks

File Description SizeFormat 
PhysRevResearch.2.033429.pdfPublished version2.5 MBAdobe PDFView/Open
Title: Ab-initio solution of the many-electron Schrödinger equation with deep neural networks
Authors: Pfau, D
Spencer, JS
Matthews, AGDG
Foulkes, WMC
Item Type: Journal Article
Abstract: Given access to accurate solutions of the many-electron Schr\"odinger equation, nearly all chemistry could be derived from first principles. Exact wavefunctions of interesting chemical systems are out of reach because they are NP-hard to compute in general, but approximations can be found using polynomially-scaling algorithms. The key challenge for many of these algorithms is the choice of wavefunction approximation, or Ansatz, which must trade off between efficiency and accuracy. Neural networks have shown impressive power as accurate practical function approximators and promise as a compact wavefunction Ansatz for spin systems, but problems in electronic structure require wavefunctions that obey Fermi-Dirac statistics. Here we introduce a novel deep learning architecture, the Fermionic Neural Network, as a powerful wavefunction Ansatz for many-electron systems. The Fermionic Neural Network is able to achieve accuracy beyond other variational quantum Monte Carlo Ans\"atze on a variety of atoms and small molecules. Using no data other than atomic positions and charges, we predict the dissociation curves of the nitrogen molecule and hydrogen chain, two challenging strongly-correlated systems, to significantly higher accuracy than the coupled cluster method, widely considered the most accurate scalable method for quantum chemistry at equilibrium geometry. This demonstrates that deep neural networks can improve the accuracy of variational quantum Monte Carlo to the point where it outperforms other ab-initio quantum chemistry methods, opening the possibility of accurate direct optimisation of wavefunctions for previously intractable molecules and solids.
Issue Date: 1-Nov-2020
Date of Acceptance: 6-Aug-2020
URI: http://hdl.handle.net/10044/1/83718
DOI: 10.1103/PhysRevResearch.2.033429
ISSN: 2643-1564
Publisher: American Physical Society
Journal / Book Title: Physical Review Research
Volume: 2
Issue: 3
Copyright Statement: © 2020 The Author(s). Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.
Keywords: physics.chem-ph
Publication Status: Published
Article Number: ARTN 033429
Online Publication Date: 2020-09-16
Appears in Collections:Condensed Matter Theory

This item is licensed under a Creative Commons License Creative Commons