Sparse Autoregressive Neural Networks for Classical Spin Systems

Abstract

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this domain. However, these neural networks are often treated as black boxes, with architectures primarily influenced by data-driven problems in computational science. Addressing this gap, we introduce a novel autoregressive neural network architecture named TwoBo, specifically designed for sparse two-body interacting spin systems. We directly incorporate the Boltzmann distribution into its architecture and parameters, resulting in enhanced convergence speed, superior free energy accuracy, and reduced trainable parameters. We perform numerical experiments on disordered, frustrated systems with more than 1000 spins on grids and random graphs, and demonstrate its advantages compared to previous autoregressive and recurrent architectures. Our findings validate a physically informed approach and suggest potential extensions to multivalued variables and many-body interaction systems, paving the way for broader applications in scientific research.

15 pages, 7 figures

References in corpus (22)

• Emergence of scaling in random networks
• Statistical mechanics of complex networks
• The Bethe lattice spin glass revisited
• Statistical physics of inference: Thresholds and algorithms
• Inverse Statistical Physics of Protein Sequences: A Key Issues Review
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Asymptotically unbiased estimation of physical observables with neural samplers
• Attention-based Quantum Tomography
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Chaotic, memory and cooling rate effects in spin glasses: Is the Edwards-Anderson model a good spin glass?
• From Tensor Network Quantum States to Tensorial Recurrent Neural Networks
• Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
• Analysis and Optimization of Population Annealing
• Calculating Renyi Entropies with Neural Autoregressive Quantum States
• A Bayesian generative neural network framework for epidemic inference problems
• Metastability of the Ising model on random regular graphs at zero temperature
• Supplementing Recurrent Neural Networks with Annealing to Solve Combinatorial Optimization Problems
• Solving Statistical Mechanics on Sparse Graphs with Feedback Set Variational Autoregressive Networks
• Hierarchical autoregressive neural networks for statistical systems
• The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
• Population annealing with topological defect driven nonlocal updates for spin systems with quenched disorder

Cited by in corpus (5)

• Rényi entanglement entropy of spin chain with Generative Neural Networks
• Performance of machine-learning-assisted Monte Carlo in sampling from simple statistical physics models
• Efficient Optimization of Variational Autoregressive Networks with Natural Gradient
• Nearest-Neighbours Neural Network architecture for efficient sampling of statistical physics models
• Large-scale portfolio optimization with variational neural annealing