{"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/asymptotic-optimality-of-adaptive-importance","title":"Asymptotic optimality of adaptive importance sampling","arxiv_id":"1806.00989","date":"2018-06-04","proceeding":"NeurIPS 2018 12","authors":["Bernard Delyon","François Portier"],"abstract":"Adaptive importance sampling (AIS) uses past samples to update the\n\\textit{sampling policy} $q_t$ at each stage $t$. Each stage $t$ is formed with\ntwo steps : (i) to explore the space with $n_t$ points according to $q_t$ and\n(ii) to exploit the current amount of information to update the sampling\npolicy. The very fundamental question raised in this paper concerns the\nbehavior of empirical sums based on AIS. Without making any assumption on the\nallocation policy $n_t$, the theory developed involves no restriction on the\nsplit of computational resources between the explore (i) and the exploit (ii)\nstep. It is shown that AIS is asymptotically optimal : the asymptotic behavior\nof AIS is the same as some \"oracle\" strategy that knows the targeted sampling\npolicy from the beginning. From a practical perspective, weighted AIS is\nintroduced, a new method that allows to forget poor samples from early stages.","url_abs":"http://arxiv.org/abs/1806.00989v2","url_pdf":"http://arxiv.org/pdf/1806.00989v2.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":"asymptotic-optimality-of-adaptive-importance","repo_url":"https://github.com/portierf/AIS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.00989","atlas_url":"https://app.syntology.ai/?focus=1806.00989","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}