Nearest-Neighbours Neural Network architecture for efficient sampling of statistical physics models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Del Bono, Luca Maria, Ricci-Tersenghi, Federico, Zamponi, Francesco
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915264736526336
author Del Bono, Luca Maria
Ricci-Tersenghi, Federico
Zamponi, Francesco
author_facet Del Bono, Luca Maria
Ricci-Tersenghi, Federico
Zamponi, Francesco
contents The task of sampling efficiently the Gibbs-Boltzmann distribution of disordered systems is important both for the theoretical understanding of these models and for the solution of practical optimization problems. Unfortunately, this task is known to be hard, especially for spin glasses at low temperatures. Recently, many attempts have been made to tackle the problem by mixing classical Monte Carlo schemes with newly devised Neural Networks that learn to propose smart moves. In this article we introduce the Nearest-Neighbours Neural Network (4N) architecture, a physically-interpretable deep architecture whose number of parameters scales linearly with the size of the system and that can be applied to a large variety of topologies. We show that the 4N architecture can accurately learn the Gibbs-Boltzmann distribution for the two-dimensional Edwards-Anderson model, and specifically for some of its most difficult instances. In particular, it captures properties such as the energy, the correlation function and the overlap probability distribution. Finally, we show that the 4N performance increases with the number of layers, in a way that clearly connects to the correlation length of the system, thus providing a simple and interpretable criterion to choose the optimal depth.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19483
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nearest-Neighbours Neural Network architecture for efficient sampling of statistical physics models
Del Bono, Luca Maria
Ricci-Tersenghi, Federico
Zamponi, Francesco
Disordered Systems and Neural Networks
Statistical Mechanics
Computational Physics
The task of sampling efficiently the Gibbs-Boltzmann distribution of disordered systems is important both for the theoretical understanding of these models and for the solution of practical optimization problems. Unfortunately, this task is known to be hard, especially for spin glasses at low temperatures. Recently, many attempts have been made to tackle the problem by mixing classical Monte Carlo schemes with newly devised Neural Networks that learn to propose smart moves. In this article we introduce the Nearest-Neighbours Neural Network (4N) architecture, a physically-interpretable deep architecture whose number of parameters scales linearly with the size of the system and that can be applied to a large variety of topologies. We show that the 4N architecture can accurately learn the Gibbs-Boltzmann distribution for the two-dimensional Edwards-Anderson model, and specifically for some of its most difficult instances. In particular, it captures properties such as the energy, the correlation function and the overlap probability distribution. Finally, we show that the 4N performance increases with the number of layers, in a way that clearly connects to the correlation length of the system, thus providing a simple and interpretable criterion to choose the optimal depth.
title Nearest-Neighbours Neural Network architecture for efficient sampling of statistical physics models
topic Disordered Systems and Neural Networks
Statistical Mechanics
Computational Physics
url https://arxiv.org/abs/2407.19483