{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:19:44Z","timestamp":1772554784527,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62376015"],"award-info":[{"award-number":["62376015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U22B2038"],"award-info":[{"award-number":["U22B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["42471441"],"award-info":[{"award-number":["42471441"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3549591","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:50:50Z","timestamp":1741715450000},"page":"1379-1393","source":"Crossref","is-referenced-by-count":7,"title":["Online Federated Reproduced Gradient Descent With Time-Varying Global Optima"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0922-2641","authenticated-orcid":false,"given":"Yifu","family":"Lin","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9130-5736","authenticated-orcid":false,"given":"Wenling","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4019-970X","authenticated-orcid":false,"given":"Jia","family":"Song","sequence":"additional","affiliation":[{"name":"School of Astronautics, Beihang University (BUAA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7804-368X","authenticated-orcid":false,"given":"Xiaoming","family":"Li","sequence":"additional","affiliation":[{"name":"Research Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3232192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3311024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3232630"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3124599"},{"key":"ref5","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.,","author":"McMahan","year":"2017"},{"key":"ref6","first-page":"1","article-title":"Adaptive federated optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddi","year":"2021"},{"issue":"5","key":"ref7","first-page":"5902","article-title":"Fedexp: Speeding up federated averaging via extrapolation","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"35","author":"Jhunjhunwala","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3292497"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30714-9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-38794-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3309988"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29763-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3316588"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3356257"},{"key":"ref15","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn., Proc. Mach. Learn. Res.","volume":"139","author":"Collins","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3144699"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3514802"},{"key":"ref18","first-page":"10334","article-title":"Is local SGD better than minibatch SGD?","volume-title":"Proc. 37th Int. Conf. Mach. Learn., ser. Proc. Mach. Learn. Res.","volume":"119","author":"Woodworth","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01565"},{"key":"ref20","first-page":"32991","article-title":"Dynamic regularized sharpness aware minimization in federated learning: Approaching global consistency and smooth landscape","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Sun","year":"2023"},{"key":"ref21","first-page":"1","article-title":"Federated learning based on dynamic regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Durmus","year":"2021"},{"key":"ref22","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3408631"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378161"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1145\/3423211.3425685","article-title":"FLEET: Online federated learning via staleness awareness and performance prediction","volume-title":"Proc. 21st Int. Middleware Conf.","author":"Damaskinos","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683589"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i08.7021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3409755"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT54713.2023.10206945"},{"key":"ref31","first-page":"27439","article-title":"Federated online and bandit convex optimization","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Patel","year":"2023"},{"key":"ref32","first-page":"3","article-title":"Effective and privacy-preserving federated online learning to rank","volume-title":"Proc. ACM SIGIR Int. Conf. Theory Inf. Retrieval","author":"Wang","year":"2021"},{"key":"ref33","article-title":"Online stochastic convex optimization: Wasserstein distance variation","author":"Shames","year":"2020"},{"key":"ref34","article-title":"Distributionally time-varying online stochastic optimization under polyak-\u0141ojasiewicz condition with application in conditional value-at-risk statistical learning","author":"Pun","year":"2023"},{"issue":"147","key":"ref35","first-page":"1","article-title":"Stochastic optimization under distributional drift","volume-title":"J. Mach. Learn. Res.","volume":"24","author":"Cutler","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2996178"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3124187"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42470-5"},{"key":"ref39","first-page":"1","article-title":"The clear benchmark: Continual learning on real-world imagery","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Lin","year":"2021"},{"key":"ref40","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2019.0198"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2021.109896","article-title":"Deterministic error bounds for kernel-based learning techniques under bounded noise","volume":"134","author":"Maddalena","year":"2021","journal-title":"Automatica"},{"key":"ref44","article-title":"Positive definite kernels: Past, present and future","volume":"4","author":"FasshauerG","year":"2011","journal-title":"Dolomites Res. Notes Approximation"},{"key":"ref45","article-title":"Random features for large-scale kernel machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Rahimi","year":"2007"},{"issue":"1","key":"ref46","first-page":"1613","article-title":"Large scale online kernel learning","volume":"17","author":"Lu","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","first-page":"5200","article-title":"SGD: General analysis and improved rates","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Gower","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2781640"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310499"},{"issue":"196","key":"ref50","first-page":"1","article-title":"COKE: Communication-censored decentralized kernel learning","volume-title":"J. Mach. Learn. Res.","volume":"22","author":"Xu","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3316672"},{"key":"ref53","first-page":"4519","article-title":"Tighter theory for local SGD on identical and heterogeneous data","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist.","volume":"108","author":"Khaled","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01728"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1849"},{"key":"ref56","first-page":"649","article-title":"Kernel regression in high dimensions: Refined analysis beyond double descent","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","volume":"130","author":"Liu","year":"2021"},{"issue":"1","key":"ref57","first-page":"689","article-title":"The rank of a random matrix","volume-title":"Appl. Math. Comput.","volume":"185","author":"Feng","year":"2007"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/10918691.pdf?arnumber=10918691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T19:07:33Z","timestamp":1742843253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10918691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3549591","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}