Machine learning configuration interaction for ab initio potential energy curves

Abstract

The concept of machine learning configuration interaction (MLCI) [J. Chem. Theory Comput. 2018, 14, 5739], where an artificial neural network (ANN) learns on the fly to select important configurations, is further developed so that accurate ab initio potential energy curves can be efficiently calculated. This development includes employing the artificial neural network also as a hash function for the efficient deletion of duplicates on the fly so that the singles and doubles space does not need to be stored and this barrier to scalability is removed. In addition configuration state functions are introduced into the approach so that pure spin states are guaranteed, and the transferability of data between geometries is exploited. This improved approach is demonstrated on potential energy curves for the nitrogen molecule, water, and carbon monoxide. The results are compared with full configuration interaction values, when available, and different transfer protocols are investigated. It is shown that, for all of the considered systems, accurate potential energy curves can now be efficiently computed with MLCI. For the potential curves of N${}_2$ and CO, MLCI can achieve lower errors than stochastically selecting configurations while also using substantially less processor hours.

This document is the unedited Author's version of a Submitted Work that was subsequently accepted for publication in The Journal of Chemical Theory and Computation, copyright American Chemical Society after peer review. To access the final edited and published work see https://pubs.acs.org/articlesonrequest/AOR-7xICeRwJFp8nKTCDecNs

References in corpus (21)

• Heat-bath Configuration Interaction: An efficient selected CI algorithm inspired by heat-bath sampling
• A Mountaineering Strategy to Excited States: Highly-Accurate Reference Energies and Benchmarks
• Alchemical and structural distribution based representation for improved QML
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Quantum Package 2.0: An Open-Source Determinant-Driven Suite of Programs
• Machine learning of molecular properties: locality and active learning
• Selected configuration interaction dressed by perturbation
• Adaptive multiconfigurational wave functions
• Machine Learning Configuration Interaction
• Virtual orbital many-body expansions: A possible route towards the full configuration interaction limit
• Excitation energies from diffusion Monte Carlo using selected Configuration Interaction nodes
• Many-Body Expanded Full Configuration Interaction. I. Weakly Correlated Regime
• Deterministic construction of nodal surfaces within quantum Monte Carlo: the case of FeS
• Many-Body Expanded Full Configuration Interaction. II. Strongly Correlated Regime
• Coordinate descent full configuration interaction
• Applying Monte Carlo configuration interaction to transition metal dimers: exploring the balance between static and dynamic correlation
• Development of Monte Carlo configuration interaction: Natural orbitals and second-order perturbation theory
• Approaching exact hyperpolarizabilities via sum-over-states Monte Carlo configuration interaction
• Artificial neural networks for density-functional optimizations in fermionic systems
• Multireference X-Ray Emission and Absorption Spectroscopy calculations from Monte Carlo Configuration Interaction
• Spin-adapted selected configuration interaction in a determinant basis

Cited by in corpus (9)

• Quantum Machine Learning for Chemistry and Physics
• The Shape of Full Configuration Interaction to Come
• ADAPT-QSCI: Adaptive Construction of an Input State for Quantum-Selected Configuration Interaction
• Quantum-Selected Configuration Interaction: classical diagonalization of Hamiltonians in subspaces selected by quantum computers
• Improved Optimization for the Neural-network Quantum States and Tests on the Chromium Dimer
• A Non-stochastic Optimization Algorithm for Neural-network Quantum States
• Data-driven Refinement of Electronic Energies from Two-Electron Reduced-Density-Matrix Theory
• Quantum-selected configuration interaction with time-evolved state
• Neural-network-supported basis optimizer for the configuration interaction problem in quantum many-body clusters: Feasibility study and numerical proof