articleNature CommunicationsOct 5, 2017GOLD OA

Bypassing the Kohn-Sham equations with machine learning

FBFelix BrockherdeLVLeslie VogtLLLi LiMEMark E. TuckermanKBKieron Burke

Max Planck Institute of Microstructure Physics · Technische Universität Berlin · +6 more institutions

PubMed
Indexed inarxivcrossrefdoajpubmed

Abstract

Last year, at least 30,000 scientific papers used the Kohn-Sham scheme of density functional theory to solve electronic structure problems in a wide variety of scientific fields. Machine learning holds the promise of learning the energy functional via examples, bypassing the need to solve the Kohn-Sham equations. This should yield substantial savings in computer time, allowing larger systems and/or longer time-scales to be tackled, but attempts to machine-learn this functional have been limited by the need to find its derivative. The present work overcomes this difficulty by directly learning the density-potential and energy-density maps for test systems and various molecules. We perform the first molecular…

Citation impact

609
total citations
FWCI
28.65
Percentile
100%
References
61
Citations per year

Authors

6
  • FB
    Felix BrockherdeCorresponding

    Max Planck Institute of Microstructure Physics, Technische Universität Berlin

  • LV
    Leslie Vogt

    New York University

  • LL
    Li Li

    University of California, Irvine

  • ME
    Mark E. Tuckerman

    New York University Shanghai, Courant Institute of Mathematical Sciences, New York University

  • KB
    Kieron Burke

    University of California, Irvine

Topics & keywords

Keywords
  • Density functional theory
  • Variety (cybernetics)
  • Scheme (mathematics)
  • Work (physics)
  • Computational learning theory
  • Dynamical systems theory
  • Transfer of learning
  • Time-dependent density functional theory
No related works found for this paper.

Funding