{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:38:45Z","timestamp":1759333125987,"version":"3.37.3"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"Graduate Research Fellowships from the National Science Foundation and from Stanford University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tit.2022.3213630","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:20:36Z","timestamp":1665433236000},"page":"1795-1823","source":"Crossref","is-referenced-by-count":1,"title":["First-Order Bayesian Regret Analysis of Thompson Sampling"],"prefix":"10.1109","volume":"69","author":[{"given":"Sebastien","family":"Bubeck","sequence":"first","affiliation":[{"name":"Department of Mathematics, Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9166-8185","authenticated-orcid":false,"given":"Mark","family":"Sellke","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/11894841_20"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2013.0598"},{"key":"ref3","first-page":"23","article-title":"Online learning with feedback graphs: Beyond bandits","volume-title":"Proc. Annu. Conf. Learn. Theory","volume":"40","author":"Alon"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref5","first-page":"39","article-title":"Analysis of Thompson sampling for the multi-armed bandit problem","volume-title":"Proc. 25th Annu. Conf. Learn. Theory (COLT)","volume":"23","author":"Agrawal"},{"key":"ref6","first-page":"4","article-title":"Open problem: First-order regret bounds for contextual bandits","volume-title":"Proc. Conf. Learn. Theory","author":"Agarwal"},{"key":"ref7","first-page":"1","article-title":"Fighting bandits with a new kind of smoothness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Abernethy"},{"key":"ref8","first-page":"186","article-title":"Make the minority great again: First-order regret bound for contextual bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref9","first-page":"266","article-title":"Bandit convex optimization: \u221aT regret in one dimension","volume-title":"Proc. 28th Annu. Conf. Learn. Theory (COLT)","author":"Bubeck"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/258128.258179"},{"key":"ref11","first-page":"1","article-title":"An empirical evaluation of Thompson sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Chapelle"},{"key":"ref12","first-page":"18907","article-title":"Efficient first-order contextual bandits: Prediction, allocation, and triangular discrimination","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Foster"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176996452"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84628-696-4_13"},{"key":"ref15","first-page":"93","article-title":"Hedging structured concepts","volume-title":"Proc. 23rd Annu. Conf. Learn. Theory (COLT)","author":"Koolen"},{"key":"ref16","first-page":"2965","article-title":"Mirror descent and the information ratio","volume-title":"Proc. Conf. Learn. Theory","author":"Lattimore"},{"key":"ref17","first-page":"2111","article-title":"An information-theoretic approach to minimax regret in partial monitoring","volume-title":"Proc. Conf. Learn. Theory (COLT)","author":"Lattimore"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1204"},{"key":"ref19","first-page":"592","article-title":"Feedback graph regret bounds for Thompson sampling and UCB","volume-title":"Proc. 31st Int. Conf. Algorithmic Learn. Theory (ALT)","author":"Lykouris"},{"key":"ref20","first-page":"1","article-title":"Analysis of Thompson sampling for graphical bandits without the graphs","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell. (UAI)","author":"Liu"},{"key":"ref21","first-page":"684","article-title":"From bandits to experts: On the value of side-observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mannor"},{"key":"ref22","first-page":"993","article-title":"Online learning with predictable sequences","volume-title":"Proc. Conf. Learn. Theory","author":"Rakhlin"},{"issue":"1","key":"ref23","first-page":"2442","article-title":"An information-theoretic analysis of Thompson sampling","volume":"17","author":"Russo","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10897"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref26","first-page":"11973","article-title":"Connections between mirror descent, Thompson sampling and the information ratio","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zimmert"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/10046300\/9915622-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/10046300\/09915622.pdf?arnumber=9915622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:51:58Z","timestamp":1705960318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9915622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":26,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tit.2022.3213630","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"type":"print","value":"0018-9448"},{"type":"electronic","value":"1557-9654"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}