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

Abstract

Recent years have seen a rise in the application of machine learning techniques to aid the simulation of hard-to-sample systems that cannot be studied using traditional methods. Despite the introduction of many different architectures and procedures, a wide theoretical understanding is still lacking, with the risk of suboptimal implementations. As a first step to address this gap, we provide here a complete analytic study of the widely-used Sequential Tempering procedure applied to a shallow MADE architecture for the Curie-Weiss model. The contribution of this work is twofold: firstly, we give a description of the optimal weights and of the training under Gradient Descent optimization. Secondly, we compare what happens in Sequential Tempering with and without the addition of local Metropolis Monte Carlo steps. We are thus able to give theoretical predictions on the best procedure to apply in this case. This work establishes a clear theoretical basis for the integration of machine learning techniques into Monte Carlo sampling and optimization.

17 pages, 10 figures

References in corpus (14)

• Comparing Monte Carlo methods for finding ground states of Ising spin glasses: population annealing, simulated annealing and parallel tempering
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Unveiling the structure of wide flat minima in neural networks
• Understanding population annealing Monte Carlo simulations
• Generative diffusion in very large dimensions
• Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
• Lee-Yang theory of the Curie-Weiss model and its rare fluctuations
• Hierarchical autoregressive neural networks for statistical systems
• Wavelet Conditional Renormalization Group
• The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
• Policy-guided Monte Carlo on general state spaces: Application to glass-forming mixtures
• Sparse Autoregressive Neural Networks for Classical Spin Systems
• A Very Effective and Simple Diffusion Reconstruction for the Diluted Ising Model
• Nearest-Neighbours Neural Network architecture for efficient sampling of statistical physics models

Cited by in corpus (2)

• Computational Methods toward Ultrastable Glasses
• Uncertainty in AI-driven Monte Carlo simulations