{"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/output-sensitive-adaptive-metropolis-hastings","title":"Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs","arxiv_id":"1501.05677","date":"2015-01-22","proceeding":null,"authors":["David Tolpin","Jan Willem van de Meent","Brooks Paige","Frank Wood"],"abstract":"We introduce an adaptive output-sensitive Metropolis-Hastings algorithm for\nprobabilistic models expressed as programs, Adaptive Lightweight\nMetropolis-Hastings (AdLMH). The algorithm extends Lightweight\nMetropolis-Hastings (LMH) by adjusting the probabilities of proposing random\nvariables for modification to improve convergence of the program output. We\nshow that AdLMH converges to the correct equilibrium distribution and compare\nconvergence of AdLMH to that of LMH on several test problems to highlight\ndifferent aspects of the adaptation scheme. We observe consistent improvement\nin convergence on the test problems.","url_abs":"http://arxiv.org/abs/1501.05677v2","url_pdf":"http://arxiv.org/pdf/1501.05677v2.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":"output-sensitive-adaptive-metropolis-hastings","repo_url":"https://bitbucket.org/dtolpin/embang","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"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}