{"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/max-value-entropy-search-for-efficient","title":"Max-value Entropy Search for Efficient Bayesian Optimization","arxiv_id":"1703.01968","date":"2017-03-06","proceeding":"ICML 2017 8","authors":["Zi Wang","Stefanie Jegelka"],"abstract":"Entropy Search (ES) and Predictive Entropy Search (PES) are popular and\nempirically successful Bayesian Optimization techniques. Both rely on a\ncompelling information-theoretic motivation, and maximize the information\ngained about the $\\arg\\max$ of the unknown function; yet, both are plagued by\nthe expensive computation for estimating entropies. We propose a new criterion,\nMax-value Entropy Search (MES), that instead uses the information about the\nmaximum function value. We show relations of MES to other Bayesian optimization\nmethods, and establish a regret bound. We observe that MES maintains or\nimproves the good empirical performance of ES/PES, while tremendously\nlightening the computational burden. In particular, MES is much more robust to\nthe number of samples used for computing the entropy, and hence more efficient\nfor higher dimensional problems.","url_abs":"http://arxiv.org/abs/1703.01968v3","url_pdf":"http://arxiv.org/pdf/1703.01968v3.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":"max-value-entropy-search-for-efficient","repo_url":"https://github.com/zi-w/Max-value-Entropy-Search","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"max-value-entropy-search-for-efficient","repo_url":"https://github.com/SK-tklab/BayesianOptimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"max-value-entropy-search-for-efficient","repo_url":"https://github.com/kiudee/bayes-skopt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"max-value-entropy-search-for-efficient","repo_url":"https://github.com/svedel/greattunes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"bayesian-optimisation","task_name":"Bayesian Optimisation"},{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1703.01968","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}