Saved in:
Bibliographic Details
Main Authors: Ren, Yixiong, Zhou, Jianhui
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.16598
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917876120682496
author Ren, Yixiong
Zhou, Jianhui
author_facet Ren, Yixiong
Zhou, Jianhui
contents Monte Carlo methods are widely used importance sampling techniques for studying complex physical systems. Integrating these methods with deep learning has significantly improved efficiency and accuracy in high-dimensional problems and complex system simulations. However, these neural network-enhanced Monte Carlo methods still face challenges such as slow sampling speeds, statistical bias, and inaccuracies in the ground state. To address these issues, we propose a variational evolutionary network, which utilizes neural networks for variational free energy and combines evolutionary algorithms for sampling. During the sampling process, we construct generation and selection operators to filter samples based on importance, thereby achieving efficient importance sampling. We demonstrate that this sampling method provides an upper bound on the ground-state energy, enhancing both sampling efficiency and ground-state accuracy. Moreover, we numerically examine our method in two-dimensional Ising model and Sherrington-Kirkpatrick Model for spin glass. Thus, our algorithm could offer improved accuracy in handling complex energy landscapes and significantly enhance computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16598
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Variational Evolutionary Network for Statistical Physics Systems
Ren, Yixiong
Zhou, Jianhui
Disordered Systems and Neural Networks
Statistical Mechanics
Monte Carlo methods are widely used importance sampling techniques for studying complex physical systems. Integrating these methods with deep learning has significantly improved efficiency and accuracy in high-dimensional problems and complex system simulations. However, these neural network-enhanced Monte Carlo methods still face challenges such as slow sampling speeds, statistical bias, and inaccuracies in the ground state. To address these issues, we propose a variational evolutionary network, which utilizes neural networks for variational free energy and combines evolutionary algorithms for sampling. During the sampling process, we construct generation and selection operators to filter samples based on importance, thereby achieving efficient importance sampling. We demonstrate that this sampling method provides an upper bound on the ground-state energy, enhancing both sampling efficiency and ground-state accuracy. Moreover, we numerically examine our method in two-dimensional Ising model and Sherrington-Kirkpatrick Model for spin glass. Thus, our algorithm could offer improved accuracy in handling complex energy landscapes and significantly enhance computational efficiency.
title Variational Evolutionary Network for Statistical Physics Systems
topic Disordered Systems and Neural Networks
Statistical Mechanics
url https://arxiv.org/abs/2412.16598