Machine Learning Configuration Interaction

Abstract

We propose the concept of machine learning configuration interaction (MLCI) whereby an artificial neural network is trained on-the-fly to predict important new configurations in an iterative selected configuration interaction procedure. We demonstrate that the neural network can discriminate between important and unimportant configurations, that it has not been trained on, much better than by chance. MLCI is then used to find compact wavefunctions for carbon monoxide at both stretched and equilibrium geometries. We also consider the multireference problem of the water molecule with elongated bonds. Results are contrasted with those from other ways of selecting configurations: first-order perturbation, random selection and Monte Carlo configuration interaction. Compared with these other serial calculations, this prototype MLCI is competitive in its accuracy, converges in significantly fewer iterations than the stochastic approaches, and requires less time for the higher-accuracy computations.

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-dANIFXJKzRAyR99E6hbh

References in corpus (8)

• Heat-bath Configuration Interaction: An efficient selected CI algorithm inspired by heat-bath sampling
• Semistochastic Heat-bath Configuration Interaction method: selected configuration interaction with semistochastic perturbation theory
• Adaptive multiconfigurational wave functions
• Deterministic construction of nodal surfaces within quantum Monte Carlo: the case of FeS
• 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
• Multireference X-Ray Emission and Absorption Spectroscopy calculations from Monte Carlo Configuration Interaction

Cited by in corpus (30)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Quantum Package 2.0: An Open-Source Determinant-Driven Suite of Programs
• Quantum Machine Learning for Chemistry and Physics
• QUESTDB: a database of highly-accurate excitation energies for the electronic structure community
• Ab-initio quantum chemistry with neural-network wavefunctions
• Selected Configuration Interaction in a Basis of Cluster State Tensor Products
• The Shape of Full Configuration Interaction to Come
• Many-Body Expanded Full Configuration Interaction. II. Strongly Correlated Regime
• Machine learning configuration interaction for ab initio potential energy curves
• ADAPT-QSCI: Adaptive Construction of an Input State for Quantum-Selected Configuration Interaction
• Accurate full configuration interaction correlation energy estimates for five- and six-membered rings
• How accurate are EOM-CC4 vertical excitation energies?
• Reference Energies for Cyclobutadiene: Automerization and Excited States
• State-Specific Coupled-Cluster Methods for Excited States
• Ground- and Excited-State Dipole Moments and Oscillator Strengths of Full Configuration Interaction Quality
• Ligand additivity relationships enable efficient exploration of transition metal chemical space
• Quantum-Selected Configuration Interaction: classical diagonalization of Hamiltonians in subspaces selected by quantum computers
• Deep-learning approach for the atomic configuration interaction problem on large basis sets
• Ground and Excited State First-Order Properties in Many-Body Expanded Full Configuration Interaction Theory
• Spin-adapted selected configuration interaction in a determinant basis
• A Parallel, Distributed Memory Implementation of the Adaptive Sampling Configuration Interaction Method
• A Non-stochastic Optimization Algorithm for Neural-network Quantum States
• Quantum-selected configuration interaction with time-evolved state
• Data-driven Refinement of Electronic Energies from Two-Electron Reduced-Density-Matrix Theory
• Rationale for the Extrapolation Procedure in Selected Configuration Interaction
• Selected Configuration Interaction for Resonances
• Neural-network-supported basis optimizer for the configuration interaction problem in quantum many-body clusters: Feasibility study and numerical proof
• Machine Learning Wavefunction
• Further Development of iCIPT2 for Strongly Correlated Electrons
• Iterative Configuration Interaction with Selection