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

Abstract

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.

Second version. 11 pages; SI: 5 pages

References in corpus (21)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Simulated Tempering: A New Monte Carlo Scheme
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Combinatorial Optimization with Physics-Inspired Graph Neural Networks
• A Cluster Monte Carlo Algorithm for 2-Dimensional Spin Glasses
• Efficient generative modeling of protein sequences using simple autoregressive models
• Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Graph Coloring with Physics-Inspired Graph Neural Networks
• Skipping the Replica Exchange Ladder with Normalizing Flows
• Universal critical behavior of the 2d Ising spin glass
• Finding defects in glasses through machine learning
• Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
• Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set
• Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems like Max-Cut
• Policy-guided Monte Carlo on general state spaces: Application to glass-forming mixtures
• The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
• Deep reinforced learning heuristic tested on spin-glass ground states: The larger picture
• Sparse Autoregressive Neural Networks for Classical Spin Systems
• Enhancing GNNs Performance on Combinatorial Optimization by Recurrent Feature Update
• Autoregressive model path dependence near Ising criticality

Cited by in corpus (1)

• Performance of machine-learning-assisted Monte Carlo in sampling from simple statistical physics models