{"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/derivative-free-optimization-via-repeated","title":"Derivative free optimization via repeated classification","arxiv_id":"1804.03761","date":"2018-04-11","proceeding":null,"authors":["Tatsunori B. Hashimoto","Steve Yadlowsky","John C. Duchi"],"abstract":"We develop an algorithm for minimizing a function using $n$ batched function\nvalue measurements at each of $T$ rounds by using classifiers to identify a\nfunction's sublevel set. We show that sufficiently accurate classifiers can\nachieve linear convergence rates, and show that the convergence rate is tied to\nthe difficulty of active learning sublevel sets. Further, we show that the\nbootstrap is a computationally efficient approximation to the necessary\nclassification scheme.\n  The end result is a computationally efficient derivative-free algorithm\nrequiring no tuning that consistently outperforms other approaches on\nsimulations, standard benchmarks, real-world DNA binding optimization, and\nairfoil design problems whenever batched function queries are natural.","url_abs":"http://arxiv.org/abs/1804.03761v1","url_pdf":"http://arxiv.org/pdf/1804.03761v1.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":"derivative-free-optimization-via-repeated","repo_url":"https://worksheets.codalab.org/worksheets/0x978bd1ba6b284678994c067f9c9bdb78","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.03761","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}