Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
- 24 July 2018
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 14 (9) , 4772-4779
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 off generalized density-matrix functionals.Keywords
All Related Versions
Funding Information
- Air Force Office of Scientific Research (FA9550-17-1-0102)
- Camille and Henry Dreyfus Foundation
- Resnick Sustainability Institute for Science, Energy and Sustainability, California Institute of Technology
- California Institute of Technology
This publication has 40 references indexed in Scilit:
- Machine learning of molecular electronic properties in chemical compound spaceNew Journal of Physics, 2013
- Accurate sampling using Langevin dynamicsPhysical Review E, 2007
- Potential energy surface discontinuities in local correlation methodsThe Journal of Chemical Physics, 2004
- Comparison of the boys and Pipek–Mezey localizations in the local correlation approach and automatic virtual basis selectionJournal of Computational Chemistry, 1993
- A scaled conjugate gradient algorithm for fast supervised learningNeural Networks, 1993
- Development of the Colle-Salvetti correlation-energy formula into a functional of the electron densityPhysical Review B, 1988
- Accurate spin-dependent electron liquid correlation energies for local spin density calculations: a critical analysisCanadian Journal of Physics, 1980
- Brueckner's Theory and the Method of Superposition of ConfigurationsPhysical Review B, 1958
- Note on an Approximation Treatment for Many-Electron SystemsPhysical Review B, 1934
- VII. Mathematical contributions to the theory of evolution.—III. Regression, heredity, and panmixiaPhilosophical Transactions of the Royal Society A, 1896