A Neural-Network-Based Selective Configuration Interaction Approach to Molecular Electronic Structure

TL;DR

This paper introduces a neural-network-supported selective configuration interaction method that efficiently approximates full CI results for molecules, enabling larger and extended system calculations with reduced computational cost.

Contribution

The authors develop a neural-network-based selective CI approach that significantly reduces the number of determinants needed for accurate electronic structure calculations.

Findings

Achieved near full CI accuracy with only 4x10^5 determinants for N2.

Demonstrated the method's efficiency in small molecules and potential for extended systems.

Expanded CI applicability through integration with condensed matter simulation software.

Abstract

By combining Hartree-Fock with a neural-network-supported quantum-cluster solver proposed recently in the context of solid-state lattice models, we formulate a scheme for selective neural-network configuration interaction (NNCI) calculations and implement it with various options for the type of basis set and boundary conditions. The method's performance is evaluated in studies of several small molecules as a step toward calculations of larger systems. In particular, the correlation energy in the N$_2$ molecule is compared with published full CI calculations that included nearly $10^{10}$ Slater determinants, and the results are reproduced with only $4\cdot10^{5}$ determinants using NNCI. A clear advantage is seen from increasing the set of orbitals included rather than approaching full CI for a smaller set. The method's high efficiency and implementation in a condensed matter simulation software expands the applicability of CI calculations to a wider range of problems, even extended systems through an embedding approach.