Sparse autoregressive neural networks for classical spin systems
Open Access
- 1 June 2024
- journal article
- research article
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 5 (2) , 025074
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.Keywords
All Related Versions
Funding Information
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (200336)
This publication has 39 references indexed in Scilit:
- The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systemsCommunications Physics, 2023
- A Bayesian generative neural network framework for epidemic inference problemsScientific Reports, 2022
- Hierarchical autoregressive neural networks for statistical systemsComputer Physics Communications, 2022
- Autoregressive neural-network wavefunctions for ab initio quantum chemistryNature Machine Intelligence, 2022
- Attention-based quantum tomographyMachine Learning: Science and Technology, 2021
- Variational neural annealingNature Machine Intelligence, 2021
- Solving quantum statistical mechanics with variational autoregressive networks and quantum circuitsMachine Learning: Science and Technology, 2021
- Inverse statistical physics of protein sequences: a key issues reviewReports on Progress in Physics, 2018
- Statistical physics of inference: thresholds and algorithmsAdvances in Physics, 2016
- Metastability of the Ising model on random regular graphs at zero temperatureProbability Theory and Related Fields, 2015