CaltechAUTHORS
  A Caltech Library Service

Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis

Welborn, Matthew and Cheng, Lixue and Miller, Thomas F., III (2018) Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis. Journal of Chemical Theory and Computation, 14 (9). pp. 4772-4779. ISSN 1549-9618. http://resolver.caltech.edu/CaltechAUTHORS:20180724-153741211

[img] PDF - Accepted Version
See Usage Policy.

10Mb
[img] PDF (Expanded details for small molecule predictions (corresponding to Table II), MP2 results corresponding to all CCSD results presented in the main text, and plots of ML prediction error versus total CCSD energy corresponding to Figures 2–5) - Submitted Version
See Usage Policy.

1904Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180724-153741211

Abstract

We present a machine learning (ML) method for predicting electronic structure correlation energies using Hartree–Fock input. The total correlation energy is expressed in terms of individual and pair contributions from occupied molecular orbitals, and Gaussian process regression is used to predict these contributions from a feature set that is based on molecular orbital properties, such as Fock, Coulomb, and exchange matrix elements. With the aim of maximizing transferability across chemical systems and compactness of the feature set, we avoid the usual specification of ML features in terms of atom- or geometry-specific information, such atom/element-types, bond-types, or local molecular structure. ML predictions of MP2 and CCSD energies are presented for a range of systems, demonstrating that the method maintains accuracy while providing transferability both within and across chemical families; this includes predictions for molecules with atom-types and elements that are not included in the training set. The method holds promise both in its current form and as a proof-of-principle for the use of ML in the design of generalized density-matrix functionals.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1021/acs.jctc.8b00636DOIArticle
https://pubs.acs.org/doi/suppl/10.1021/acs.jctc.8b00636PublisherSupporting Information
ORCID:
AuthorORCID
Miller, Thomas F., III0000-0002-1882-5380
Additional Information:© 2018 American Chemical Society. Received: June 24, 2018; Published: July 24, 2018. This work was supported by AFOSR award no. FA9550-17-1-0102. The authors additionally acknowledge support from the Resnick Sustainability Institute postdoctoral fellowship (M.W.), a Caltech Chemistry graduate fellowship (L.C.), and the Camille Dreyfus Teacher-Scholar Award (T.F.M.). The authors declare no competing financial interest.
Group:Resnick Sustainability Institute
Funders:
Funding AgencyGrant Number
Air Force Office of Scientific Research (AFOSR)FA9550-17-1-0102
Resnick Sustainability InstituteUNSPECIFIED
CaltechUNSPECIFIED
Camille and Henry Dreyfus FoundationUNSPECIFIED
Subject Keywords:machine learning, electron correlation, Gaussian processes, density-matrix functional theory
Record Number:CaltechAUTHORS:20180724-153741211
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180724-153741211
Official Citation:Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis. Matthew Welborn, Lixue Cheng, and Thomas F. Miller, III. Journal of Chemical Theory and Computation 2018 14 (9), 4772-4779. DOI: 10.1021/acs.jctc.8b00636
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:88221
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:24 Jul 2018 22:47
Last Modified:17 Sep 2018 21:08

Repository Staff Only: item control page