{"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/gaussian-process-optimization-in-the-bandit","title":"Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design","arxiv_id":"0912.3995","date":"2009-12-21","proceeding":null,"authors":["Niranjan Srinivas","Andreas Krause","Sham M. Kakade","Matthias Seeger"],"abstract":"Many applications require optimizing an unknown, noisy function that is\nexpensive to evaluate. We formalize this task as a multi-armed bandit problem,\nwhere the payoff function is either sampled from a Gaussian process (GP) or has\nlow RKHS norm. We resolve the important open problem of deriving regret bounds\nfor this setting, which imply novel convergence rates for GP optimization. We\nanalyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its\ncumulative regret in terms of maximal information gain, establishing a novel\nconnection between GP optimization and experimental design. Moreover, by\nbounding the latter in terms of operator spectra, we obtain explicit sublinear\nregret bounds for many commonly used covariance functions. In some important\ncases, our bounds have surprisingly weak dependence on the dimensionality. In\nour experiments on real sensor data, GP-UCB compares favorably with other\nheuristical GP optimization approaches.","url_abs":"http://arxiv.org/abs/0912.3995v4","url_pdf":"http://arxiv.org/pdf/0912.3995v4.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":"gaussian-process-optimization-in-the-bandit","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":"gaussian-process-optimization-in-the-bandit","repo_url":"https://github.com/lamourj/fastcode-gpucb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"experimental-design","task_name":"Experimental Design"}],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=0912.3995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"0912.3995"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SK-tklab/BayesianOptimization","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lamourj/fastcode-gpucb","reach":null}],"summary":{"ran_violates":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"dcdd0b5c86be9efc","entry":"sample","repo":"lamourj/fastcode-gpucb","repo_kind":"listed","path":"tester.py","file_url":"https://github.com/lamourj/fastcode-gpucb/blob/HEAD/tester.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcdd0b5c86be9efc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}