{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T11:24:47Z","timestamp":1748604287369,"version":"3.40.4"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Innovation","award":["2022ZD0208700"],"award-info":[{"award-number":["2022ZD0208700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376264"],"award-info":[{"award-number":["62376264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tkde.2024.3458419","type":"journal-article","created":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T17:30:06Z","timestamp":1727112606000},"page":"2200-2211","source":"Crossref","is-referenced-by-count":2,"title":["A Unified Framework for Bandit Online Multiclass Prediction"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3334-4649","authenticated-orcid":false,"given":"Wanjin","family":"Feng","sequence":"first","affiliation":[{"name":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4660-8092","authenticated-orcid":false,"given":"Xingyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8543-3953","authenticated-orcid":false,"given":"Peilin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4584-3453","authenticated-orcid":false,"given":"Steven C.H.","family":"Hoi","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]}],"member":"263","reference":[{"issue":"Nov","key":"ref1","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2009.36"},{"key":"ref3","first-page":"55","article-title":"Logarithmic time online multiclass prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choromanska"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390212"},{"key":"ref5","first-page":"1035","article-title":"Stochastic convex optimization with bandit feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Agarwal"},{"article-title":"Bandit-feedback online multiclass classification: Variants and tradeoffs","year":"2024","author":"Filmus","key":"ref6"},{"key":"ref7","first-page":"817","article-title":"The epoch-greedy algorithm for multi-armed bandits with side information","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Langford"},{"article-title":"Multiclass online learnability under bandit feedback","year":"2023","author":"Raman","key":"ref8"},{"key":"ref9","first-page":"1","article-title":"Multi-armed bandit for pricing","volume-title":"Proc. 12th Eur. Workshop Reinforcement Learn.","author":"Trovo"},{"key":"ref10","first-page":"1","article-title":"Online multiclass learning with","volume-title":"Proc. IEEE Glob. Commun. Conf.","author":"Shi"},{"key":"ref11","first-page":"67","article-title":"Contextual bandits for adapting treatment in a mouse model of de novo carcinogenesis","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Durand"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.53"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507176"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8463"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CEC48606.2020.9185782"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160593"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.112"},{"key":"ref18","first-page":"342","article-title":"Boosting with online binary learners for the multiclass bandit problem","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref21","first-page":"900","article-title":"A potential-based framework for online multi-class learning with partial feedback","volume-title":"Proc. 13th Artif. Intell. Statist.","author":"Wang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191245"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5016-8"},{"article-title":"An efficient bandit algorithm for $\\sqrt{T}$T-regret in online multiclass prediction?","volume-title":"Proc. Conf. Learn. Theory","author":"Abernethy","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5321-8"},{"key":"ref26","first-page":"488","article-title":"Efficient online bandit multiclass learning with $\\tilde{O}(\\sqrt{T})$O\u02dc(T) regret","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Beygelzimer"},{"key":"ref27","first-page":"167","article-title":"Logistic regression: The importance of being improper","volume-title":"Proc. Conf. Learn. Theory","author":"Foster"},{"key":"ref28","first-page":"3","article-title":"Efficient methods for online multiclass logistic regression","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Agarwal"},{"key":"ref29","first-page":"9562","article-title":"Exploiting the surrogate gap in online multiclass classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"van der Hoeven"},{"key":"ref30","first-page":"624","article-title":"Bandit multiclass linear classification: Efficient algorithms for the separable case","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Beygelzimer"},{"key":"ref31","first-page":"891","article-title":"Newtron: An efficient bandit algorithm for online multiclass prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hazan"},{"key":"ref32","first-page":"3458","article-title":"Linear contextual bandits with knapsacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Agrawal"},{"issue":"7","key":"ref33","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","first-page":"1638","article-title":"Taming the monster: A fast and simple algorithm for contextual bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"key":"ref35","first-page":"1977","article-title":"Bistro: An efficient relaxation-based method for contextual bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakhlin"},{"key":"ref36","first-page":"2159","article-title":"Efficient algorithms for adversarial contextual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Syrgkanis"},{"key":"ref37","first-page":"3","article-title":"Efficient Methods for Online Multiclass Logistic Regression","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Agarwal"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020445"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.47738\/jads.v2i2.28"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24412-4_17"},{"key":"ref41","first-page":"39","article-title":"Analysis of thompson sampling for the multi-armed bandit problem","volume-title":"Proc. Conf. Learn. Theory","author":"Agrawal"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.35940\/ijitee.L2522.1081219"},{"article-title":"Online multiclass classification based on prediction margin for partial feedback","year":"2019","author":"Kaneko","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24412-4_16"},{"key":"ref46","first-page":"127","article-title":"Thompson sampling for contextual bandits with linear payoffs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agrawal"},{"key":"ref47","first-page":"8749","article-title":"Tight regret and complexity bounds for Thompson sampling via Langevin Monte Carlo","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Huix"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00115"},{"key":"ref49","first-page":"1585","article-title":"An efficient algorithm for generalized linear bandit: Online stochastic gradient descent and Thompson sampling","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ding"},{"key":"ref50","first-page":"2071","article-title":"Provably optimal algorithms for generalized linear contextual bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref51","first-page":"10 115","article-title":"Thompson sampling via local uncertainty","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref52","first-page":"6797","article-title":"On approximate Thompson sampling with Langevin algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mazumdar"},{"key":"ref53","first-page":"1840","article-title":"New adaptive algorithms for online classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Orabona"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-006-0237-y"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3224420"},{"article-title":"Online Newton step algorithm with estimated gradient","year":"2018","author":"Liu","key":"ref56"},{"key":"ref57","first-page":"823","article-title":"Beyond logarithmic bounds in online learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Orabona"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010896012157"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-014-5474-8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539703432542"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref63","first-page":"208","article-title":"Contextual bandits with linear payoff functions","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Chu"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/10948402\/10689269.pdf?arnumber=10689269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T05:05:18Z","timestamp":1744952718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10689269\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":63,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3458419","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"type":"print","value":"1041-4347"},{"type":"electronic","value":"1558-2191"},{"type":"electronic","value":"2326-3865"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}