{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:12:56Z","timestamp":1775913176983,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["62373316"],"award-info":[{"award-number":["62373316"]}],"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":["62003287"],"award-info":[{"award-number":["62003287"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["RCYX20210609103229031"],"award-info":[{"award-number":["RCYX20210609103229031"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12201534"],"award-info":[{"award-number":["12201534"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["RCBS20210609103708017"],"award-info":[{"award-number":["RCBS20210609103708017"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373316"],"award-info":[{"award-number":["62373316"]}],"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":["62003287"],"award-info":[{"award-number":["62003287"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["RCYX20210609103229031"],"award-info":[{"award-number":["RCYX20210609103229031"]}]},{"name":"Guangdong Talent Program","award":["2021QN02X216"],"award-info":[{"award-number":["2021QN02X216"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tac.2024.3393169","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T17:36:49Z","timestamp":1713980209000},"page":"6105-6120","source":"Crossref","is-referenced-by-count":5,"title":["Distributed Stochastic Optimization Under a General Variance Condition"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9326-6670","authenticated-orcid":false,"given":"Kun","family":"Huang","sequence":"first","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5577-6963","authenticated-orcid":false,"given":"Xiao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5813-527X","authenticated-orcid":false,"given":"Shi","family":"Pu","sequence":"additional","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Stat.","author":"McMahan","year":"2017"},{"key":"ref2","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/17M1111085"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2423256"},{"key":"ref5","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2526683"},{"key":"ref7","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. Process. Syst.","author":"Lian","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3126253"},{"key":"ref9","article-title":"Optimal client sampling for federated learning","volume-title":"Trans. Mach. Learn. Res.","author":"Chen","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref11","article-title":"Better theory for SGD in the nonconvex world","author":"Khaled","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3201141"},{"key":"ref13","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref14","article-title":"On the unreasonable effectiveness of federated averaging with heterogeneous data","author":"Wang","year":"2022"},{"key":"ref15","first-page":"9310","article-title":"Tackling data heterogeneity: A new unified framework for decentralized SGD with sample-induced topology","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Huang","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3630048.3630187"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2023.3262181"},{"key":"ref18","article-title":"Differentially private federated learning with normalized updates","volume-title":"Proc. OPT: Optim. Mach. Learn.","author":"Das","year":"2022"},{"key":"ref19","first-page":"33107","article-title":"A unified convergence theorem for stochastic optimization methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2952219"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01487-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3008605"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3184770"},{"key":"ref25","first-page":"4848","article-title":"D2: Decentralized training over decentralized data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tang","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2926022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3062553"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2427360"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2427352"},{"key":"ref30","first-page":"11422","article-title":"An improved analysis of gradient tracking for decentralized machine learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Koloskova","year":"2021"},{"key":"ref31","first-page":"6281","article-title":"Minibatch vs local SGD for heterogeneous distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Woodworth","year":"2020"},{"key":"ref32","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.","author":"Yu","year":"2019"},{"key":"ref33","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li","year":"2020"},{"key":"ref34","first-page":"3556","article-title":"Local SGD: Unified theory and new efficient methods","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Gorbunov","year":"2021"},{"key":"ref35","first-page":"1055","article-title":"Can 5th generation local training methods support client sampling? Yes!","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Grudzie","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref37","first-page":"36014","article-title":"Global convergence and stability of stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Patel","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-021-01710-6"},{"key":"ref39","first-page":"4519","article-title":"Tighter theory for local SGD on identical and heterogeneous data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Khaled","year":"2020"},{"key":"ref40","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2021"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2023.2241151"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/18M1179249"},{"key":"ref45","first-page":"5200","article-title":"SGD: General analysis and improved rates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gower","year":"2019"},{"key":"ref46","first-page":"1","article-title":"Mini-batch stochastic subgradient for functional constrained optimization","author":"Singh","year":"2023","journal-title":"Optimization"},{"key":"ref47","first-page":"32304","article-title":"FedAvg converges to zero training loss linearly for overparameterized multi-layer neural networks","author":"Song","year":"2023"},{"key":"ref48","article-title":"Linear convergence of decentralized FedAvg for non-convex objectives: The interpolation regime","author":"Maralappanavar","year":"2023"},{"key":"ref49","article-title":"A unified theory of decentralized SGD with changing topology and local updates","author":"Koloskova","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref51","first-page":"233","article-title":"A convergence theorem for non negative almost supermartingales and some applications","volume-title":"Optimizing Methods in Statistics","author":"Robbins","year":"1971"},{"key":"ref52","first-page":"17309","article-title":"Random reshuffling: Simple analysis with vast improvements","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Mishchenko","year":"2020"},{"key":"ref53","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Stat. JMLR Workshop Conf. Proc.","author":"Glorot","year":"2011"},{"key":"ref54","volume-title":"Convex Analysis","volume":"11","author":"Rockafellar","year":"1997"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10654305\/10508084.pdf?arnumber=10508084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T03:30:07Z","timestamp":1736134207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":54,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3393169","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}