{"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/regret-bounds-for-meta-bayesian-optimization","title":"Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior","arxiv_id":"1811.09558","date":"2018-11-23","proceeding":"NeurIPS 2018 12","authors":["Zi Wang","Beomjoon Kim","Leslie Pack Kaelbling"],"abstract":"Bayesian optimization usually assumes that a Bayesian prior is given.\nHowever, the strong theoretical guarantees in Bayesian optimization are often\nregrettably compromised in practice because of unknown parameters in the prior.\nIn this paper, we adopt a variant of empirical Bayes and show that, by\nestimating the Gaussian process prior from offline data sampled from the same\nprior and constructing unbiased estimators of the posterior, variants of both\nGP-UCB and probability of improvement achieve a near-zero regret bound, which\ndecreases to a constant proportional to the observational noise as the number\nof offline data and the number of online evaluations increase. Empirically, we\nhave verified our approach on challenging simulated robotic problems featuring\ntask and motion planning.","url_abs":"http://arxiv.org/abs/1811.09558v1","url_pdf":"http://arxiv.org/pdf/1811.09558v1.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":"regret-bounds-for-meta-bayesian-optimization","repo_url":"https://github.com/beomjoonkim/MetaLearnBO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"motion-planning","task_name":"Motion Planning"},{"task_slug":"task-and-motion-planning","task_name":"Task and Motion Planning"}],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.09558","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}