{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:19:09Z","timestamp":1768339149665,"version":"3.49.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62003287"],"award-info":[{"award-number":["62003287"]}],"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":["62373316"],"award-info":[{"award-number":["62373316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Talent Program","award":["2021QN02X216"],"award-info":[{"award-number":["2021QN02X216"]}]},{"name":"Shenzhen Science and Technology Program","award":["RCYX20210609103229031"],"award-info":[{"award-number":["RCYX20210609103229031"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tac.2024.3471854","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:33:04Z","timestamp":1727717584000},"page":"2242-2257","source":"Crossref","is-referenced-by-count":5,"title":["CEDAS: A Compressed Decentralized Stochastic Gradient Method With Improved Convergence"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9326-6670","authenticated-orcid":false,"given":"Kun","family":"Huang","sequence":"first","affiliation":[{"name":"Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5813-527X","authenticated-orcid":false,"given":"Shi","family":"Pu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817461"},{"key":"ref2","article-title":"Decentralized deep learning with arbitrary communication compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Koloskova","year":"2020"},{"key":"ref3","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alistarh","year":"2017"},{"key":"ref4","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Bernstein","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref6","first-page":"1306","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wangni","year":"2018"},{"key":"ref7","first-page":"4452","article-title":"Sparsified SGD with memory","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Stich","year":"2018"},{"key":"ref8","first-page":"4384","article-title":"EF21: A new, simpler, theoretically better, and practically faster error feedback","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Richtrik","year":"2021"},{"key":"ref9","first-page":"5977","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alistarh","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2024.2358790"},{"key":"ref11","first-page":"7663","article-title":"Communication compression for decentralized training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tang","year":"2018"},{"key":"ref12","first-page":"3478","article-title":"Decentralized stochastic optimization and gossip algorithms with compressed communication","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Koloskova","year":"2019"},{"key":"ref13","article-title":"Linear convergent decentralized optimization with compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2926022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3180695"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3160238"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3241771"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3225515"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975212"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3145576"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3103920"},{"key":"ref22","first-page":"14171","article-title":"Practical low-rank communication compression in decentralized deep learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Vogels","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3126253"},{"key":"ref25","first-page":"5336","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lian","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/14096668X"},{"issue":"3","key":"ref27","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1109\/TSP.2018.2875898","volume":"67","author":"Yuan","year":"2018","journal-title":"IEEE Trans. Signal Process."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-354"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080248"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2018.00062"},{"key":"ref31","first-page":"6155","article-title":"DoubleSqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tang","year":"2019"},{"key":"ref32","article-title":"IntSGD: Adaptive floatless compression of stochastic gradients","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mishchenko","year":"2021"},{"key":"ref33","first-page":"18955","article-title":"Lower bounds and nearly optimal algorithms in distributed learning with communication compression","volume-title":"proc. Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Huang","year":"2022"},{"key":"ref34","article-title":"DeepSqueeze: Decentralization meets error-compensated compression","author":"Tang","year":"2019"},{"key":"ref35","article-title":"Decentralized composite optimization with compression","author":"Li","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1355-4"},{"key":"ref37","first-page":"4087","article-title":"A linearly convergent algorithm for decentralized optimization: Sending less bits for free!","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kovalev"},{"key":"ref38","first-page":"31653","article-title":"Beer: Fast $ O (1\/T)$ rate for decentralized nonconvex optimization with communication compression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Zhao","year":"2022"},{"key":"ref39","article-title":"Quantized distributed nonconvex optimization algorithms with linear convergence","author":"Xu","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3219289"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3176253"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3201141"},{"key":"ref43","first-page":"4848","article-title":"$d^{2}$: Decentralized training over decentralized data","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Tang","year":"2018"},{"issue":"58","key":"ref44","article-title":"Robust asynchronous stochastic gradient-push: Asymptotically optimal and network-independent performance for strongly convex functions","volume":"21","author":"Spiridonoff","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01487-0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3184770"},{"issue":"280","key":"ref47","first-page":"1","article-title":"Removing data heterogeneity influence enhances network topology dependence of decentralized SGD","volume":"24","author":"Yuan","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref48","first-page":"11422","article-title":"An improved analysis of gradient tracking for decentralized machine learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Koloskova","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3062553"},{"key":"ref50","first-page":"36382","article-title":"Revisiting optimal convergence rate for smooth and non-convex stochastic decentralized optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Yuan","year":"2022"},{"key":"ref51","first-page":"7111","article-title":"Optimal complexity in decentralized training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lu"},{"key":"ref52","first-page":"2324","article-title":"A one-sample decentralized proximal algorithm for non-convex stochastic composite optimization","volume-title":"Proc. 39th Conf. Uncertainty Artif. Intell.","author":"Xiao","year":"2023"},{"issue":"276","key":"ref53","first-page":"1","article-title":"On biased compression for distributed learning","volume":"24","author":"Beznosikov","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaab006"},{"key":"ref55","article-title":"Compressed communication for distributed deep learning: Survey and quantitative evaluation","author":"Xu","year":"2020"},{"key":"ref56","article-title":"A better alternative to error feedback for communication-efficient distributed learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Horvth","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3086579"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/10945509\/10700994.pdf?arnumber=10700994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T05:21:29Z","timestamp":1743225689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10700994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":59,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3471854","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":[[2025,4]]}}}