Improving neural network performance for solving quantum sign structure

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ou, Xiaowei, Huang, Tianshu, Ozolins, Vidvuds
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908573599006720
author Ou, Xiaowei
Huang, Tianshu
Ozolins, Vidvuds
author_facet Ou, Xiaowei
Huang, Tianshu
Ozolins, Vidvuds
contents Neural quantum states have emerged as a widely used approach to the numerical study of the ground states of non-stoquastic Hamiltonians. However, existing approaches often rely on a priori knowledge of the sign structure or require a separately pre-trained phase network. We introduce a modified stochastic reconfiguration method that effectively uses differing imaginary time steps to evolve the amplitude and phase. Using a larger time step for phase optimization, this method enables a simultaneous and efficient training of phase and amplitude neural networks. The efficacy of our method is demonstrated on the Heisenberg J_1-J_2 model.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02051
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving neural network performance for solving quantum sign structure
Ou, Xiaowei
Huang, Tianshu
Ozolins, Vidvuds
Quantum Physics
Strongly Correlated Electrons
Computational Physics
Neural quantum states have emerged as a widely used approach to the numerical study of the ground states of non-stoquastic Hamiltonians. However, existing approaches often rely on a priori knowledge of the sign structure or require a separately pre-trained phase network. We introduce a modified stochastic reconfiguration method that effectively uses differing imaginary time steps to evolve the amplitude and phase. Using a larger time step for phase optimization, this method enables a simultaneous and efficient training of phase and amplitude neural networks. The efficacy of our method is demonstrated on the Heisenberg J_1-J_2 model.
title Improving neural network performance for solving quantum sign structure
topic Quantum Physics
Strongly Correlated Electrons
Computational Physics
url https://arxiv.org/abs/2510.02051