Penalty and auxiliary wave function methods for electronic Excitation in neural network variational Monte Carlo

TL;DR

This paper evaluates two methods, penalty and a modified auxiliary wave function, for calculating low-lying excited states in molecules using neural network variational Monte Carlo, highlighting the robustness of the modified AW approach.

Contribution

Introduces a modified auxiliary wave function method within neural network variational Monte Carlo, demonstrating its robustness over the penalty method for excited state calculations.

Findings

Modified AW method shows superior robustness.

Application to molecular excited states is novel.

Enhances neural network ansatz toolkit for excited states.

Abstract

This study explores the application of neural network variational Monte Carlo (NN-VMC) for the computation of low-lying excited states in molecular systems. Our focus lies on the implementation and evaluation of two distinct methodologies, the penalty method and a novel modification of the auxiliary wave function (AW) method, within the framework of the FermiNet-based NN-VMC package. Importantly, this specific application has not been previously reported.Our investigation advocates for the efficacy of the modified AW method, emphasizing its superior robustness when compared to the penalty method. This methodological advancement introduces a valuable tool for the scientific community, offering a distinctive approach to target low-lying excited states. We anticipate that the modified AW method will garner interest within the research community, serving as a complementary and robust alternative to existing techniques. Moreover, this contribution enriches the ongoing development of various neural network ansatz, further expanding the toolkit available for the accurate exploration of excited states in molecular systems.