{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T07:58:16Z","timestamp":1773388696193,"version":"3.50.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CAREER-2045641"],"award-info":[{"award-number":["CAREER-2045641"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2325956"],"award-info":[{"award-number":["CNS-2325956"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SaTC-2512128"],"award-info":[{"award-number":["SaTC-2512128"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2533814"],"award-info":[{"award-number":["CNS-2533814"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fellowship Award from the Research Grants Council of Hong Kong Special Administrative Region, China","award":["CUHK PDFS2324-4S04"],"award-info":[{"award-number":["CUHK PDFS2324-4S04"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["625B2163"],"award-info":[{"award-number":["625B2163"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["CNS-2103024"],"award-info":[{"award-number":["CNS-2103024"]}]},{"name":"Research Grants Council of Hong Kong","award":["GRF-14202923"],"award-info":[{"award-number":["GRF-14202923"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2026.3663325","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T21:04:32Z","timestamp":1770757472000},"page":"3932-3946","source":"Crossref","is-referenced-by-count":0,"title":["Combinatorial Logistic Online Learning and Its Applications in Nonlinear Networked Systems"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8628-5873","authenticated-orcid":false,"given":"Xutong","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0179-196X","authenticated-orcid":false,"given":"Xiangxiang","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8043-8521","authenticated-orcid":false,"given":"Xuchuang","family":"Wang","sequence":"additional","affiliation":[{"name":"Manning College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0785-9291","authenticated-orcid":false,"given":"Carlee","family":"Joe-Wong","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9278-2254","authenticated-orcid":false,"given":"Mohammad","family":"Hajiesmaili","sequence":"additional","affiliation":[{"name":"Manning College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7466-0384","authenticated-orcid":false,"given":"John C. S.","family":"Lui","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000068"},{"issue":"79","key":"ref4","first-page":"2369","article-title":"The on-line shortest path problem under partial monitoring","volume":"8","author":"Gy\u00f6rgy","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","first-page":"1450","article-title":"Combinatorial cascading bandits","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","volume":"28","author":"Kveton"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2019.2954310"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228940"},{"key":"ref8","first-page":"1245","article-title":"Contextual combinatorial cascading bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"48","author":"Li"},{"key":"ref9","first-page":"3945","article-title":"TopRank: A practical algorithm for online stochastic ranking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Lattimore"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1832"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736824"},{"key":"ref12","article-title":"Influence maximization with bandits","author":"Vaswani","year":"2015","journal-title":"arXiv:1503.00024"},{"key":"ref13","first-page":"3026","article-title":"Online influence maximization under independent cascade model with semi-bandit feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref14","first-page":"1161","article-title":"Improving regret bounds for combinatorial semi-bandits with probabilistically triggered arms and its applications","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.53"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17177"},{"key":"ref17","first-page":"22559","article-title":"Contextual combinatorial bandits with probabilistically triggered arms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref18","first-page":"767","article-title":"Cascading bandits: Learning to rank in the cascade model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kveton"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2112"},{"key":"ref20","first-page":"14904","article-title":"Batch-size independent regret bounds for combinatorial semi-bandits with probabilistically triggered arms or independent arms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783271"},{"key":"ref22","first-page":"4199","article-title":"Online learning to rank in stochastic click models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zoghi"},{"key":"ref23","first-page":"1","article-title":"Multi-armed bandit for pricing","volume-title":"Proc. 12th Eur. Workshop Reinforcement Learn.","author":"Trovo"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2005.852876"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DYSPAN.2010.5457857"},{"key":"ref26","article-title":"Cost-effective online multi-LLM selection with versatile reward models","author":"Dai","year":"2024","journal-title":"arXiv:2405.16587"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11763"},{"key":"ref28","first-page":"3691","article-title":"Instance-wise minimax-optimal algorithms for logistic bandits","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Abeille"},{"key":"ref29","first-page":"546","article-title":"Jointly efficient and optimal algorithms for logistic bandits","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Faury"},{"key":"ref30","first-page":"2465","article-title":"Batch-size independent regret bounds for the combinatorial multi-armed bandit problem","volume-title":"Proc. Conf. Learn. Theory","author":"Merlis"},{"key":"ref31","first-page":"3052","article-title":"Improved optimistic algorithms for logistic bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Faury"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CISS50987.2021.9400228"},{"key":"ref33","first-page":"151","article-title":"Combinatorial multi-armed bandit: General framework and applications","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"14","author":"Chen"},{"key":"ref34","first-page":"586","article-title":"Parametric bandits: The generalized linear case","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Filippi"},{"issue":"1","key":"ref35","first-page":"1746","article-title":"Combinatorial multi-armed bandit and its extension to probabilistically triggered arms","volume":"17","author":"Chen","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00085"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TON.2024.3519568"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2870521"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682895"},{"key":"ref41","first-page":"343","article-title":"PCC vivace: Online-learning congestion control","volume-title":"Proc. 15th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Dong"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2003.1248658"},{"key":"ref43","first-page":"459","article-title":"QoE assessment model for video streaming service using QoS parameters in wired-wireless network","volume-title":"Proc. 14th Int. Conf. Adv. Commun. Technol. (ICACT)","author":"Jong Kim"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3448250"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3423442"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/405"},{"issue":"78","key":"ref47","first-page":"1","article-title":"Logistic matrix factorization for implicit feedback data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Johnson"},{"key":"ref48","article-title":"A unified confidence sequence for generalized linear models, with applications to bandits","author":"Lee","year":"2024","journal-title":"arXiv:2407.13977"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1214\/09-EJS521"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1214\/24-AOS2395"},{"key":"ref51","first-page":"697","article-title":"Nearly tight bounds for the continuum-armed bandit problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"17","author":"Kleinberg"},{"key":"ref52","first-page":"975","article-title":"Lipschitz bandits: Regret lower bound and optimal algorithms","volume-title":"Proc. Conf. Learn. Theory","author":"Magureanu"},{"key":"ref53","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","author":"Srinivas","year":"2009","journal-title":"arXiv:0912.3995"},{"key":"ref54","first-page":"11492","article-title":"Neural contextual bandits with UCB-based exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref55","first-page":"3199","article-title":"Beyond UCB: Optimal and efficient contextual bandits with regression oracles","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Foster"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2011.2181864"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2012.01.001"},{"key":"ref58","first-page":"535","article-title":"Tight regret bounds for stochastic combinatorial semi-bandits","volume-title":"Proc. AISTATS","author":"Kveton"},{"key":"ref59","first-page":"2116","article-title":"Combinatorial bandits revisited","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"28","author":"Combes"},{"key":"ref60","article-title":"Combinatorial multivariant multi-armed bandits with applications to episodic reinforcement learning and beyond","author":"Liu","year":"2024","journal-title":"arXiv:2406.01386"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3058685"},{"key":"ref62","first-page":"3251","article-title":"Contextual combinatorial multi-armed bandits with volatile arms and submodular reward","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chen"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737654"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2636139"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1015"},{"key":"ref66","first-page":"19","article-title":"An unbiased offline evaluation of contextual bandit algorithms with generalized linear models","volume-title":"Proc. Workshop Line Trading Explor. Exploitation","author":"Li"},{"key":"ref67","first-page":"208","article-title":"Contextual bandits with linear payoff functions","volume-title":"Proc. 40th Int. Conf. Artif. Intell. Statist.","author":"Chu"},{"key":"ref68","first-page":"2312","article-title":"Improved algorithms for linear stochastic bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"24","author":"Abbasi-Yadkori"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3275851"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681269"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2876823"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956769"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6871676"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621257"},{"key":"ref75","article-title":"Multi-agent conversational online learning for adaptive LLM response identification","author":"Dai","year":"2025","journal-title":"arXiv:2501.01849v1"},{"key":"ref76","article-title":"Online multi-LLM selection via contextual bandits under unstructured context evolution","author":"Poon","year":"2025","journal-title":"arXiv:2506.17670"},{"key":"ref77","article-title":"InvestLM: A large language model for investment using financial domain instruction tuning","author":"Yang","year":"2023","journal-title":"arXiv:2309.13064"},{"key":"ref78","article-title":"FrugalGPT: How to use large language models while reducing cost and improving performance","author":"Chen","year":"2023","journal-title":"arXiv:2305.05176"},{"key":"ref79","volume-title":"Poe","author":"Platform","year":"2024"},{"key":"ref80","article-title":"A dynamic LLM-powered agent network for task-oriented agent collaboration","author":"Liu","year":"2023","journal-title":"arXiv:2310.02170"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.14778\/3137765.3137827"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref83","first-page":"29741","article-title":"Online (multinomial) logistic bandit: Improved regret and constant computation cost","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Zhang"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/10723154\/11317935\/11391544-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11391544.pdf?arnumber=11391544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:53:34Z","timestamp":1773377614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11391544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/ton.2026.3663325","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}