{"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/approximate-inference-via-weighted-rademacher","title":"Approximate Inference via Weighted Rademacher Complexity","arxiv_id":"1801.09028","date":"2018-01-27","proceeding":null,"authors":["Jonathan Kuck","Ashish Sabharwal","Stefano Ermon"],"abstract":"Rademacher complexity is often used to characterize the learnability of a\nhypothesis class and is known to be related to the class size. We leverage this\nobservation and introduce a new technique for estimating the size of an\narbitrary weighted set, defined as the sum of weights of all elements in the\nset. Our technique provides upper and lower bounds on a novel generalization of\nRademacher complexity to the weighted setting in terms of the weighted set\nsize. This generalizes Massart's Lemma, a known upper bound on the Rademacher\ncomplexity in terms of the unweighted set size. We show that the weighted\nRademacher complexity can be estimated by solving a randomly perturbed\noptimization problem, allowing us to derive high-probability bounds on the size\nof any weighted set. We apply our method to the problems of calculating the\npartition function of an Ising model and computing propositional model counts\n(#SAT). Our experiments demonstrate that we can produce tighter bounds than\ncompeting methods in both the weighted and unweighted settings.","url_abs":"http://arxiv.org/abs/1801.09028v1","url_pdf":"http://arxiv.org/pdf/1801.09028v1.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":"approximate-inference-via-weighted-rademacher","repo_url":"https://github.com/ermongroup/weighted-rademacher","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"lemma","task_name":"LEMMA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}