Deep-learning approach for the atomic configuration interaction problem on large basis sets

Abstract

High-precision atomic structure calculations require accurate modelling of electronic correlations typically addressed via the configuration interaction (CI) problem on a multiconfiguration wave function expansion. The latter can easily become challenging or infeasibly large even for advanced supercomputers. Here we develop a deep-learning approach which allows to preselect the most relevant configurations out of large CI basis sets until the targeted energy precision is achieved. The large CI computation is thereby replaced by a series of smaller ones performed on an iteratively expanding basis subset managed by a neural network. While dense architectures as used in quantum chemistry fail, we show that a convolutional neural network naturally accounts for the physical structure of the basis set and allows for robust and accurate CI calculations. The method was benchmarked on basis sets of moderate size allowing for the direct CI calculation, and further demonstrated on prohibitively large sets where the direct computation is not possible.

References in corpus (1)

• $\text{Direct}Q\text{-Value Determination of the}{\beta }^{-}\text{Decay of}{}^{187}\text{Re}$

Cited by in corpus (5)

• Graspg -- An extension to Grasp2018 based on Configuration State Function Generators
• Computing excited states of molecules using normalizing flows
• Neural-network-supported basis optimizer for the configuration interaction problem in quantum many-body clusters: Feasibility study and numerical proof
• SOLAX: A Python solver for fermionic quantum systems with neural network support
• $\text{Ab initio}$ multiconfigurational calculations of experimentally significant energy levels and transition rates in Lr I $\left(Z=103\right)$