{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:13:27Z","timestamp":1784646807960,"version":"3.55.0"},"reference-count":48,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176051"],"award-info":[{"award-number":["62176051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["20240101370JC"],"award-info":[{"award-number":["20240101370JC"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Program of Jilin Provincial Department of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3531356","type":"journal-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T19:09:36Z","timestamp":1737400176000},"page":"549-558","source":"Crossref","is-referenced-by-count":4,"title":["On the Convergence of Decentralized Stochastic Gradient Descent With Biased Gradients"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7960-4086","authenticated-orcid":false,"given":"Yiming","family":"Jiang","sequence":"first","affiliation":[{"name":"Key Laboratory for Applied Statistics of MOE, School of Mathematics and Statistics, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-0288","authenticated-orcid":false,"given":"Helei","family":"Kang","sequence":"additional","affiliation":[{"name":"Key Laboratory for Applied Statistics of MOE, School of Mathematics and Statistics, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2906-079X","authenticated-orcid":false,"given":"Jinlan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Changchun Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9663-9743","authenticated-orcid":false,"given":"Dongpo","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory for Applied Statistics of MOE, School of Mathematics and Statistics, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"25","author":"Dean","year":"2012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2423256"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref4","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"27","author":"Li","year":"2014"},{"issue":"6","key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2031203"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/130943170"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3008605"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3184770"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3297053"},{"key":"ref12","first-page":"756","article-title":"Learning classifiers when the training data is not iid","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Dundar","year":"2007"},{"key":"ref13","first-page":"1","article-title":"Stochastic first order methods in smooth convex optimization","author":"Devolder","year":"2011","journal-title":"Universit\u00e9 catholique de Louvain, Center Operations Res. Econometrics (CORE)"},{"key":"ref14","first-page":"1458","article-title":"Convergence rates of inexact proximal-gradient methods for convex optimization","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"24","author":"Schmidt","year":"2011"},{"key":"ref15","first-page":"5977","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"31","author":"Alistarh","year":"2018"},{"key":"ref16","first-page":"1306","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"31","author":"Wangni","year":"2018"},{"key":"ref17","first-page":"693","article-title":"Hogwild!: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"24","author":"Niu","year":"2011"},{"key":"ref18","first-page":"8133","article-title":"Rethinking gradient sparsification as total error minimization","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"34","author":"Sahu","year":"2021"},{"key":"ref19","first-page":"2663","article-title":"A stochastic gradient method with an exponential convergence rate for finite training sets","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"25","author":"Roux","year":"2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1030-6"},{"key":"ref21","first-page":"4009","article-title":"SARAH: A novel method for machine learning problems using stochastic recursive gradient","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"6","author":"Nguyen","year":"2017"},{"key":"ref22","first-page":"1672","article-title":"Refined convergence and topology learning for decentralized sgd with heterogeneous data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"206","author":"Bars","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref25","first-page":"1","article-title":"On the convergence of SGD with biased gradients","volume-title":"Proc. Int. Conf. Mach. Learn., Workshop","author":"Ajalloeian","year":"2020"},{"key":"ref26","article-title":"Decentralized deep learning with arbitrary communication compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Koloskova","year":"2020"},{"key":"ref27","first-page":"5336","article-title":"Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"30","author":"Lian","year":"2017"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1007\/s10957-010-9737-7","article-title":"Distributed stochastic subgradient projection algorithms for convex optimization","volume":"147","author":"Ram","year":"2010","journal-title":"J. Optim. Theory Appl."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2161027"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3126253"},{"key":"ref31","first-page":"4848","article-title":"$D^{2}$: Decentralized training over decentralized data","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Tang","year":"2018"},{"key":"ref32","article-title":"Clipping for nonconvex DSGD under weak smoothness assumptions","author":"Sun","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0677-5"},{"key":"ref34","first-page":"819","article-title":"(Bandit) convex optimization with biased noisy gradient oracles","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","volume":"51","author":"Hu","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01486-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/DSW.2019.8755807"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3062553"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3097211"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-022-00432-5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01487-0"},{"key":"ref41","first-page":"3478","article-title":"Decentralized stochastic optimization and gossip algorithms with compressed communication","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Koloskova","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201711"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2989393"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196503"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2818081"},{"key":"ref46","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Yu","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3262181"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2017.2698261"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/10847585.pdf?arnumber=10847585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T19:15:51Z","timestamp":1738178151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10847585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3531356","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}