{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/optimal-structure-and-parameter-learning-of","title":"Optimal structure and parameter learning of Ising models","arxiv_id":"1612.05024","date":"2016-12-15","proceeding":null,"authors":["Andrey Y. Lokhov","Marc Vuffray","Sidhant Misra","Michael Chertkov"],"abstract":"Reconstruction of structure and parameters of an Ising model from binary\nsamples is a problem of practical importance in a variety of disciplines,\nranging from statistical physics and computational biology to image processing\nand machine learning. The focus of the research community shifted towards\ndeveloping universal reconstruction algorithms which are both computationally\nefficient and require the minimal amount of expensive data. We introduce a new\nmethod, Interaction Screening, which accurately estimates the model parameters\nusing local optimization problems. The algorithm provably achieves perfect\ngraph structure recovery with an information-theoretically optimal number of\nsamples, notably in the low-temperature regime which is known to be the hardest\nfor learning. The efficacy of Interaction Screening is assessed through\nextensive numerical tests on synthetic Ising models of various topologies with\ndifferent types of interactions, as well as on a real data produced by a D-Wave\nquantum computer. This study shows that the Interaction Screening method is an\nexact, tractable and optimal technique universally solving the inverse Ising\nproblem.","url_abs":"http://arxiv.org/abs/1612.05024v2","url_pdf":"http://arxiv.org/pdf/1612.05024v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"optimal-structure-and-parameter-learning-of","repo_url":"https://github.com/lanl-ansi/inverse_ising","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.05024","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}