{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:09:57Z","timestamp":1774022997958,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1003203"],"award-info":[{"award-number":["2018YFB1003203"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tnnls.2021.3087579","type":"journal-article","created":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T19:40:42Z","timestamp":1624390842000},"page":"7755-7764","source":"Crossref","is-referenced-by-count":9,"title":["Proximal Online Gradient Is Optimum for Dynamic Regret: A General Lower Bound"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8352-0092","authenticated-orcid":false,"given":"Yawei","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Cyberspace Security, Dongguan University of Technology, Dongguan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9651-1061","authenticated-orcid":false,"given":"Shuang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA"}]},{"given":"Kuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Dongguan University of Technology, Dongguan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4886-9974","authenticated-orcid":false,"given":"Lailong","family":"Luo","sequence":"additional","affiliation":[{"name":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5474-4764","authenticated-orcid":false,"given":"Jianping","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Dongguan University of Technology, Dongguan, China"}]},{"given":"Ji","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1323","article-title":"Adaptive online learning in dynamic environments","author":"zhang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref38","first-page":"2943","article-title":"Shifting regret, mirror descent, and matrices","author":"gy\u00f6rgy","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn (ICML)"},{"key":"ref33","article-title":"Online gradient descent in function space","author":"zhu","year":"2015","journal-title":"arXiv 1512 02394"},{"key":"ref32","first-page":"402","article-title":"Adaptive algorithms for online convex optimization with long-term constraints","volume":"48","author":"jenatton","year":"2016","journal-title":"Proc The 33rd Int Conf Mach Learn (ICML)"},{"key":"ref31","first-page":"235","article-title":"Online learning with non-convex losses and non-stationary regret","volume":"84","author":"gao","year":"2018","journal-title":"Proc 21st Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2797423"},{"key":"ref37","article-title":"Online optimization and regret guarantees for non-additive long-term constraints","author":"jenatton","year":"2016","journal-title":"arXiv 1602 05394"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2750109"},{"key":"ref35","first-page":"1","article-title":"Online optimization with gradual variations","volume":"23","author":"chiang","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2015.1408"},{"key":"ref28","first-page":"398","article-title":"Online optimization: Competing with dynamic comparators","author":"jadbabaie","year":"2015","journal-title":"Proc Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2743462"},{"key":"ref29","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref1","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","author":"zinkevich","year":"2003","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref20","first-page":"604","article-title":"Online learning and blackwell approachability with partial monitoring: Optimal convergence rates","volume":"54","author":"kwon","year":"2017","journal-title":"Proc 20th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref22","first-page":"579","article-title":"Dynamical Models and tracking regret in online convex programming","author":"hall","year":"2013","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref21","first-page":"1186","article-title":"Online learning with noisy side observations","volume":"51","author":"koc\u00e1k","year":"2016","journal-title":"Proc 19th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799379"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2015.2404790"},{"key":"ref26","first-page":"1","article-title":"Improved dynamic regret for non-degenerate functions","author":"zhang","year":"2017","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref25","first-page":"449","article-title":"Tracking slowly moving clairvoyant: Optimal dynamic regret of online learning with true and noisy gradient","author":"yang","year":"2016","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref50","first-page":"1405","article-title":"Strongly adaptive online learning","author":"daniely","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn (ICML)"},{"key":"ref51","first-page":"1286","article-title":"Achieving all with no parameters: Adanormalhedge","author":"luo","year":"2015","journal-title":"Proc Conf Learn Theory (COLT)"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-009-0206-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5599-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1248377.1248431"},{"key":"ref40","first-page":"1","article-title":"Optimal strategies and minimax lower bounds for online convex games","author":"abernethy","year":"2008","journal-title":"Proc 19th Ann Conf Learning Theory (COLT)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315181"},{"key":"ref13","first-page":"1764","article-title":"Online learning: Stochastic, constrained, and smoothed adversaries","author":"rakhlin","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref14","first-page":"288","article-title":"Zeroth-order online alternating direction method of multipliers: Convergence analysis and applications","volume":"84","author":"liu","year":"2018","journal-title":"Proc 21st Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3065950"},{"key":"ref16","first-page":"1","article-title":"Large scale online kernel learning","volume":"17","author":"lu","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref17","first-page":"2037","article-title":"Online ensemble multi-kernel learning adaptive to non-stationary and adversarial environments","volume":"84","author":"shen","year":"2018","journal-title":"Proc 21st Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref18","first-page":"1","article-title":"Online convex optimization in the bandit setting: Gradient descent without a gradient","author":"flaxman","year":"2005","journal-title":"Proc ACM\/SIAM Symp Discrete Algorithms (SODA)"},{"key":"ref19","article-title":"Online bandit learning against an adaptive adversary: From regret to policy regret","author":"arora","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn (ICML)"},{"key":"ref4","first-page":"848","article-title":"Accelerating online convex optimization via adaptive prediction","volume":"51","author":"mohri","year":"2016","journal-title":"Proc 19th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"ref6","first-page":"943","article-title":"Improved strongly adaptive online learning using coin betting","volume":"54","author":"jun","year":"2017","journal-title":"Proc 20th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref5","first-page":"5882","article-title":"Dynamic regret of strongly adaptive methods","author":"zhang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT.2018.8600081"},{"key":"ref7","first-page":"1","article-title":"Differentially private online learning","volume":"23","author":"jain","year":"2012","journal-title":"Proc Int Conf Learn Theory (COLT)"},{"key":"ref49","first-page":"1732","article-title":"Competing with automata-based expert sequences","volume":"84","author":"mohri","year":"2018","journal-title":"Proc 21st Int Conf Artif Intell Statist"},{"key":"ref9","first-page":"277","article-title":"Online learning to rank with feedback at the top","volume":"51","author":"chaudhuri","year":"2016","journal-title":"Proc 19th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref46","first-page":"1","article-title":"A closer look at adaptive regret","volume":"17","author":"adamskiy","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref45","article-title":"Efficient tracking of a growing number of experts","author":"mourtada","year":"2017","journal-title":"arXiv 1708 09811"},{"key":"ref48","first-page":"471","article-title":"Mirror descent meets fixed share (and feels no regret)","author":"cesa-bianchi","year":"2012","journal-title":"Proc NIPS"},{"key":"ref47","first-page":"3972","article-title":"Tracking the best expert in non-stationary stochastic environments","author":"wei","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007424614876"},{"key":"ref41","article-title":"A modern introduction to online learning","author":"orabona","year":"2019","journal-title":"arXiv 1912 13213"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2209627"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/11503415_14"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9966944\/09462561.pdf?arnumber=9462561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T19:54:47Z","timestamp":1671479687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9462561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":52,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3087579","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}