{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T21:58:40Z","timestamp":1778623120350,"version":"3.51.4"},"reference-count":47,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T00:00:00Z","timestamp":1718928000000},"content-version":"vor","delay-in-days":20,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T00:00:00Z","timestamp":1718928000000},"content-version":"tdm","delay-in-days":20,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"crossref","award":["200336"],"award-info":[{"award-number":["200336"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>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.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad5783","type":"journal-article","created":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T18:42:36Z","timestamp":1718217756000},"page":"025074","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Sparse autoregressive neural networks for classical spin systems"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9897-7543","authenticated-orcid":true,"given":"Indaco","family":"Biazzo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3888-5003","authenticated-orcid":true,"given":"Dian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8887-4356","authenticated-orcid":true,"given":"Giuseppe","family":"Carleo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,6,21]]},"reference":[{"key":"mlstad5783bib1","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1103\/RevModPhys.77.137","article-title":"The Kuramoto model: a simple paradigm for synchronization phenomena","volume":"77","author":"Acebr\u00f3n","year":"2005","journal-title":"Rev. Mod. Phys."},{"key":"mlstad5783bib2","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1103\/RevModPhys.74.47","article-title":"Statistical mechanics of complex networks","volume":"74","author":"Albert","year":"2002","journal-title":"Rev. Mod. Phys."},{"key":"mlstad5783bib3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.97.033301","article-title":"Analysis and optimization of population annealing","volume":"97","author":"Amey","year":"2018","journal-title":"Phys. Rev. E"},{"key":"mlstad5783bib4","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1126\/science.286.5439.509","article-title":"Emergence of scaling in random networks","volume":"286","author":"Barab\u00e1si","year":"1999","journal-title":"Science"},{"key":"mlstad5783bib5","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1038\/s42256-022-00461-z","article-title":"Autoregressive neural-network wavefunctions for ab initio quantum chemistry","volume":"4","author":"Barrett","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"mlstad5783bib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2022.108502","article-title":"Hierarchical autoregressive neural networks for statistical systems","volume":"281","author":"Bia\u0142as","year":"2022","journal-title":"Comput. Phys. Commun."},{"key":"mlstad5783bib7","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1038\/s42005-023-01416-5","article-title":"The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems","volume":"6","author":"Biazzo","year":"2023","journal-title":"Commun. Phys."},{"key":"mlstad5783bib8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-20898-x","article-title":"A bayesian generative neural network framework for epidemic inference problems","volume":"12","author":"Biazzo","year":"2022","journal-title":"Sci. Rep."},{"key":"mlstad5783bib9","author":"Biazzo","year":"2024"},{"key":"mlstad5783bib10","first-page":"1877","article-title":"Language models are few-shot learners","volume":"vol 33","author":"Brown","year":"2020"},{"key":"mlstad5783bib11","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1137\/S1052623400382467","article-title":"Rank-two relaxation heuristics for MAX-CUT and other binary quadratic programs","volume":"12","author":"Burer","year":"2002","journal-title":"SIAM J. Optim."},{"key":"mlstad5783bib12","doi-asserted-by":"publisher","first-page":"01LT01","DOI":"10.1088\/2632-2153\/ac362b","article-title":"Attention-based quantum tomography","volume":"3","author":"Cha","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad5783bib13","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1137\/1.9781611977042.5","article-title":"McSparse: exact solutions of sparse maximum cut and sparse unconstrained binary quadratic optimization problems","author":"Charfreitag","year":"2022"},{"key":"mlstad5783bib14","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acbe91","article-title":"Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems","volume":"4","author":"Ciarella","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad5783bib15","first-page":"1","article-title":"The Ising model is NP-complete","volume":"33","author":"Cipra","year":"2000","journal-title":"SIAM News"},{"key":"mlstad5783bib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.109.144202","article-title":"Population annealing with topological defect driven nonlocal updates for spin systems with quenched disorder","volume":"109","author":"Cirauqui","year":"2024","journal-title":"Phys. Rev. B"},{"key":"mlstad5783bib17","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6633\/aa9965","article-title":"Inverse statistical physics of protein sequences: a key issues review","volume":"81","author":"Cocco","year":"2018","journal-title":"Rep. Prog. Phys."},{"key":"mlstad5783bib18","article-title":"Residual energy-based models for text generation","author":"Deng","year":"2020"},{"key":"mlstad5783bib19","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/s00440-015-0682-0","article-title":"Metastability of the Ising model on random regular graphs at zero temperature","volume":"167","author":"Dommers","year":"2017","journal-title":"Probab. Theory Relat. Fields"},{"key":"mlstad5783bib20","article-title":"Compositional visual generation with energy based models","volume":"vol 33","author":"Du","year":"2020"},{"key":"mlstad5783bib21","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1287\/ijoc.2017.0798","article-title":"What works best when? a systematic evaluation of heuristics for Max-Cut and QUBO","volume":"30","author":"Dunning","year":"2018","journal-title":"INFORMS J. Comput."},{"key":"mlstad5783bib22","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1088\/0305-4608\/5\/5\/017","article-title":"Theory of spin glasses","volume":"5","author":"Edwards","year":"1975","journal-title":"J. Phys. F: Met. Phys."},{"key":"mlstad5783bib23","first-page":"881","article-title":"MADE: Masked autoencoder for distribution estimation","volume":"vol 37","author":"Germain","year":"2015"},{"key":"mlstad5783bib24","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"mlstad5783bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.023358","article-title":"Recurrent neural network wave functions","volume":"2","author":"Hibat-Allah","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstad5783bib26","doi-asserted-by":"publisher","first-page":"952","DOI":"10.1038\/s42256-021-00401-3","article-title":"Variational neural annealing","volume":"3","author":"Hibat-Allah","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"mlstad5783bib27","doi-asserted-by":"publisher","first-page":"38","DOI":"10.3390\/condmat7020038","article-title":"Neural annealing and visualization of autoregressive neural networks in the newman-moore model","volume":"7","author":"Inack","year":"2022","journal-title":"Condens. Matter"},{"key":"mlstad5783bib28","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acb895","article-title":"Supplementing recurrent neural networks with annealing to solve combinatorial optimization problems","volume":"4","author":"Khandoker","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad5783bib29","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba19d","article-title":"Solving quantum statistical mechanics with variational autoregressive networks and quantum circuits","volume":"2","author":"Liu","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad5783bib30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.128.090501","article-title":"Autoregressive neural network for simulating open quantum systems via a probabilistic formulation","volume":"128","author":"Luo","year":"2022","journal-title":"Phys. Rev. Lett."},{"key":"mlstad5783bib31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.101.053312","article-title":"Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks","volume":"101","author":"McNaughton","year":"2020","journal-title":"Phys. Rev. E"},{"key":"mlstad5783bib32","author":"Mezard","year":"2009"},{"key":"mlstad5783bib33","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/PL00011099","article-title":"The bethe lattice spin glass revisited","volume":"20","author":"M\u00e9zard","year":"2001","journal-title":"Eur. Phys. J. B"},{"key":"mlstad5783bib34","doi-asserted-by":"publisher","DOI":"10.1142\/0271","volume":"vol 9","author":"Mezard","year":"1986","journal-title":"Spin glass theory and beyond: An Introduction to the Replica Method and Its Applications"},{"key":"mlstad5783bib35","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1126\/science.1073287","article-title":"Analytic and algorithmic solution of random satisfiability problems","volume":"297","author":"M\u00e9zard","year":"2002","journal-title":"Science"},{"key":"mlstad5783bib36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.101.023304","article-title":"Asymptotically unbiased estimation of physical observables with neural samplers","volume":"101","author":"Nicoli","year":"2020","journal-title":"Phys. Rev. E"},{"key":"mlstad5783bib37","doi-asserted-by":"publisher","first-page":"1468","DOI":"10.1103\/PhysRevB.24.1468","article-title":"Critical behavior of the Baxter\u2013Wu model with quenched impurities","volume":"24","author":"Novotny","year":"1981","journal-title":"Phys. Rev. B"},{"key":"mlstad5783bib38","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.103.012103","article-title":"Solving statistical mechanics on sparse graphs with feedback-set variational autoregressive networks","volume":"103","author":"Pan","year":"2021","journal-title":"Phys. Rev. E"},{"key":"mlstad5783bib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.63.174412","article-title":"Chaotic, memory and cooling rate effects in spin glasses: evaluation of the Edwards\u2013Anderson model","volume":"63","author":"Picco","year":"2001","journal-title":"Phys. Rev. B"},{"key":"mlstad5783bib40","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.020503","article-title":"Deep autoregressive models for the efficient variational simulation of many-body quantum systems","volume":"124","author":"Sharir","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstad5783bib41","volume":"vol 4","author":"Stein","year":"2013"},{"key":"mlstad5783bib42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.102.062413","article-title":"Calculating R\u00e9nyi entropies with neural autoregressive quantum states","volume":"102","author":"Wang","year":"2020","journal-title":"Phys. Rev. A"},{"key":"mlstad5783bib43","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.3.L042024","article-title":"Unbiased Monte Carlo cluster updates with autoregressive neural networks","volume":"3","author":"Wu","year":"2021","journal-title":"Phys. Rev. Res."},{"key":"mlstad5783bib44","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.5.L032001","article-title":"From tensor-network quantum states to tensorial recurrent neural networks","volume":"5","author":"Wu","year":"2023","journal-title":"Phys. Rev. Res."},{"key":"mlstad5783bib45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.080602","article-title":"Solving statistical mechanics using variational autoregressive networks","volume":"122","author":"Wu","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"mlstad5783bib46","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1103\/RevModPhys.54.235","article-title":"The Potts model","volume":"54","author":"Wu","year":"1982","journal-title":"Rev. Mod. Phys."},{"key":"mlstad5783bib47","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1080\/00018732.2016.1211393","article-title":"Statistical physics of inference: thresholds and algorithms","volume":"65","author":"Zdeborov\u00e1","year":"2016","journal-title":"Adv. Phys."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T06:37:47Z","timestamp":1718951867000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5783"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,1]]},"references-count":47,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,6,21]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad5783","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2632-2153\/AD5783\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD5783\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD5783\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD5783\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD5783\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD5783\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD5783\/v2\/response1","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,1]]},"assertion":[{"value":"Sparse autoregressive neural networks for classical spin systems","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-02-26","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-06-12","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-06-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}