{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:00:41Z","timestamp":1777874441933,"version":"3.51.4"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473292"],"award-info":[{"award-number":["62473292"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["62473292"],"award-info":[{"award-number":["62473292"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["62088101"],"award-info":[{"award-number":["62088101"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcyb.2024.3514833","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T20:48:34Z","timestamp":1770238114000},"page":"2754-2764","source":"Crossref","is-referenced-by-count":0,"title":["Nonconvex Federated Composite Optimization With Random Reshuffling and Biased Compression"],"prefix":"10.1109","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0134-6929","authenticated-orcid":false,"given":"Haibao","family":"Tian","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, College of Electronics and Information Engineering, State Key Laboratory of Autonomous Intelligent Unmanned System, Frontiers Science Center for Intelligent Autonomous Systems, Ministry of Education, Shanghai Research Institute for Intelligent Autonomous Systems, and Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4938-0468","authenticated-orcid":false,"given":"Xiuxian","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, College of Electronics and Information Engineering, State Key Laboratory of Autonomous Intelligent Unmanned System, Frontiers Science Center for Intelligent Autonomous Systems, Ministry of Education, Shanghai Research Institute for Intelligent Autonomous Systems, and Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4860-4519","authenticated-orcid":false,"given":"Shanying","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Stat.","author":"McMahan"},{"key":"ref2","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3090260"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3247365"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3350387"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3185418"},{"key":"ref7","first-page":"12253","article-title":"Federated composite optimization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Yuan"},{"key":"ref8","first-page":"1508","article-title":"Fast composite optimization and statistical recovery in federated learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Bao"},{"key":"ref9","first-page":"30326","article-title":"FedDR\u2013randomized Douglas-Rachford splitting algorithms for nonconvex federated composite optimization","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Dinh"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243080"},{"key":"ref12","first-page":"15750","article-title":"ProxSkip: Yes! local gradient steps provably lead to communication acceleration! finally!","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Mishchenko"},{"key":"ref13","first-page":"15718","article-title":"Proximal and federated random reshuffling","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Mishchenko"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-35289-8","volume-title":"Neural Networks: Tricks of the Trade","author":"Montavon","year":"2012"},{"key":"ref16","first-page":"17309","article-title":"Random reshuffling: Simple analysis with vast improvements","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Mishchenko"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_26"},{"key":"ref18","article-title":"Minibatch vs local SGD with shuffling: Tight convergence bounds and beyond","author":"Yun","year":"2022","journal-title":"arXiv:2110.10342"},{"key":"ref19","first-page":"4384","article-title":"EF21: A new, simpler, theoretically better, and practically faster error feedback","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Richt\u00e1rik"},{"key":"ref20","article-title":"EF21 with bells & whistles: Practical algorithmic extensions of modern error feedback","author":"Fatkhullin","year":"2021","journal-title":"arXiv:2110.032941"},{"key":"ref21","article-title":"Federated optimization algorithms with random reshuffling and gradient compression","author":"Sadiev","year":"2022","journal-title":"arXiv:2206.07021"},{"key":"ref22","first-page":"1","article-title":"Analysis of error feedback in compressed federated non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref23","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Reisizadeh"},{"key":"ref24","article-title":"Unified optimal analysis of the (stochastic) gradient method","author":"Stich","year":"2019","journal-title":"arXiv:1907.04232"},{"key":"ref25","first-page":"4703","article-title":"SGD without replacement: Sharper rates for general smooth convex functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nagaraj"},{"key":"ref26","first-page":"17526","article-title":"SGD with shuffling: Optimal rates without component convexity and large epoch requirements","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ahn"},{"key":"ref27","article-title":"Server-side stepsizes and sampling without replacement provably help in federated optimization","author":"Malinovsky","year":"2022","journal-title":"arXiv:2201.11066"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2021.102199"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.011.2000501"},{"key":"ref30","article-title":"Understanding top-k sparsification in distributed deep learning","author":"Shi","year":"2019","journal-title":"arXiv:1911.08772"},{"key":"ref31","first-page":"129","article-title":"Natural compression for distributed deep learning","volume-title":"Proc. Math. Sci. Mach. Learn.","author":"Horv\u00f3th"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/473"},{"key":"ref33","first-page":"4447","article-title":"Sparsified SGD with memory","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Stich"},{"key":"ref34","article-title":"signSGD with majority vote is communication efficient and fault tolerant","author":"Bernstein","year":"2018","journal-title":"arXiv:1810.05291"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3280938"},{"key":"ref36","first-page":"3252","article-title":"Error feedback fixes SignSGD and other gradient compression schemes","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref37","article-title":"On biased compression for distributed learning","author":"Beznosikov","year":"2024","journal-title":"arXiv:2002.12410"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref39","article-title":"Federated learning with regularized client participation","author":"Malinovsky","year":"2023","journal-title":"arXiv:2302.03662"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611974997","volume-title":"First-Order Methods in Optimization","author":"Beck","year":"2017"},{"key":"ref41","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref42","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016","journal-title":"arXiv:1603.04467"},{"key":"ref43","first-page":"7057","article-title":"FedSplit: An algorithmic framework for fast federated optimization","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Pathak"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3262181"},{"key":"ref45","first-page":"2350","article-title":"Federated learning with compression: Unified analysis and sharp guarantees","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","author":"Haddadpour"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/11481828\/11372125.pdf?arnumber=11372125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:48:35Z","timestamp":1777578515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11372125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":45,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2024.3514833","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}