{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:44:34Z","timestamp":1774539874535,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tpami.2025.3610169","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:37:31Z","timestamp":1757957851000},"page":"1158-1170","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Batch Size Time Evolving Stochastic Gradient Descent for Federated Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1032-5346","authenticated-orcid":false,"given":"Xuming","family":"An","sequence":"first","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2296-6370","authenticated-orcid":false,"given":"Yong","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7532-0496","authenticated-orcid":false,"given":"Han","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Federated optimization: Distributed optimization beyond the datacenter","author":"Kone\u010dn\u00fd","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3033286"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3195956"},{"key":"ref4","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref5","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref6","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Li","year":"2020"},{"key":"ref7","first-page":"1","article-title":"Federated learning based on dynamic regularization","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Acar","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3115952"},{"key":"ref9","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Yu","year":"2019"},{"key":"ref10","first-page":"1","article-title":"Slowmo: Improving communication-efficient distributed SGD with slow momentum","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref11","article-title":"FedCM: Federated learning with client-level momentum","author":"Xu","year":"2021"},{"key":"ref12","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. 27th Ann. Conf. Neural Inf. Proc.","author":"Johnson","year":"2013"},{"key":"ref13","first-page":"2348","article-title":"Non-convex finite-sum optimization via SCSG methods","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lei","year":"2017"},{"key":"ref14","first-page":"4762","article-title":"History-gradient aided batch size adaptation for variance reduced algorithms","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Ji","year":"2020"},{"key":"ref15","first-page":"1504","article-title":"Automated inference with adaptive batches","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"De","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/19M1256919"},{"key":"ref17","first-page":"1753","article-title":"On the ineffectiveness of variance reduced optimization for deep learning","volume-title":"Proc. 32nd Ann. Conf. Neural Inf. Proc.","author":"Defazio","year":"2019"},{"key":"ref18","first-page":"1","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Yang","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3196503"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3129809"},{"key":"ref21","first-page":"2672","article-title":"A stochastic gradient method with an exponential convergence rate for finite training sets","volume-title":"Proc. 26th Ann. Conf. Neural Inf. Proc.","author":"Roux","year":"2012"},{"key":"ref22","first-page":"1646","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","volume-title":"Proc. 28th Ann. Conf. Neural Inf. Proc.","author":"Defazio","year":"2014"},{"key":"ref23","first-page":"2613","article-title":"SARAH: A novel method for machine learning problems using stochastic recursive gradient","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Nguyen","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-022-00375-x"},{"key":"ref25","first-page":"3925","article-title":"Stochastic nested variance reduced gradient descent for nonconvex optimization","volume-title":"Proc. 32nd Ann. Conf. Neural Inf. Proc.","author":"Zhou","year":"2018"},{"key":"ref26","first-page":"687","article-title":"SPIDER: Near-optimal non-convex optimization via stochastic path-integrated differential estimator","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Fang","year":"2018"},{"key":"ref27","first-page":"2403","article-title":"Spiderboost and momentum: Faster variance reduction algorithms","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3000512"},{"key":"ref29","article-title":"Parallel restarted spider\u2013communication efficient distributed nonconvex optimization with optimal computation complexity","author":"Sharma","year":"2019"},{"key":"ref30","first-page":"496","article-title":"Faster non-convex federated learning via global and local momentum","volume-title":"Proc. 38th Conf. Uncertainty Artif. Intell.","author":"Das","year":"2022"},{"key":"ref31","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","author":"Karimireddy","year":"2020"},{"key":"ref32","first-page":"7872","article-title":"Bias-variance reduced local SGD for less heterogeneous federated learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Murata","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/s21155124"},{"key":"ref34","first-page":"29553","article-title":"Federated-em with heterogeneity mitigation and variance reduction","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Dieuleveut","year":"2021"},{"key":"ref35","article-title":"Partial variance reduction improves non-convex federated learning on heterogeneous data","author":"Li","year":"2022"},{"key":"ref36","first-page":"165","article-title":"Optimal distributed online prediction using mini-batches","volume":"13","author":"Dekel","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/110830629"},{"key":"ref38","article-title":"Improving the convergence of SGD through adaptive batch sizes","author":"Sievert","year":"2019"},{"key":"ref39","first-page":"2251","article-title":"Stopwasting my gradients: Practical SVRG","volume-title":"Proc. 28th Ann. Conf. Neural Inf.","author":"Babanezhad","year":"2015"},{"key":"ref40","article-title":"Improving the convergence of SGD through adaptive batch sizes","author":"Sievert","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3112139"},{"key":"ref42","first-page":"10334","article-title":"Is local SGD better than minibatch SGD?","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Woodworth","year":"2020"},{"key":"ref43","article-title":"ADABatch: Adaptive batch sizes for training deep neural networks","author":"Devarakonda","year":"2017"},{"key":"ref44","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref45","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref46","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01198-w"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11345188\/11164526.pdf?arnumber=11164526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:59Z","timestamp":1768255259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164526\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3610169","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}