{"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/learning-the-distribution-with-largest-mean","title":"Learning the distribution with largest mean: two bandit frameworks","arxiv_id":"1702.00001","date":"2017-01-31","proceeding":null,"authors":["Emilie Kaufmann","Aurélien Garivier"],"abstract":"Over the past few years, the multi-armed bandit model has become increasingly\npopular in the machine learning community, partly because of applications\nincluding online content optimization. This paper reviews two different\nsequential learning tasks that have been considered in the bandit literature ;\nthey can be formulated as (sequentially) learning which distribution has the\nhighest mean among a set of distributions, with some constraints on the\nlearning process. For both of them (regret minimization and best arm\nidentification) we present recent, asymptotically optimal algorithms. We\ncompare the behaviors of the sampling rule of each algorithm as well as the\ncomplexity terms associated to each problem.","url_abs":"http://arxiv.org/abs/1702.00001v3","url_pdf":"http://arxiv.org/pdf/1702.00001v3.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":"learning-the-distribution-with-largest-mean","repo_url":"https://github.com/jsfunc/best-arm-identification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.00001","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}