{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:35:17Z","timestamp":1782833717122,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ericsson Canada"},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council (NSERC) of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong Research Grants Council (RGC) Early Career Scheme","award":["22200324"],"award-info":[{"award-number":["22200324"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/ton.2025.3530460","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T18:50:04Z","timestamp":1737571804000},"page":"1309-1325","source":"Crossref","is-referenced-by-count":3,"title":["Exploring Temporal Similarity for Joint Computation and Communication in Online Distributed Optimization"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-8382","authenticated-orcid":false,"given":"Juncheng","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7223-8865","authenticated-orcid":false,"given":"Min","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer, and Software Engineering, Ontario Tech University, Oshawa, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1800-1322","authenticated-orcid":false,"given":"Ben","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3539-9624","authenticated-orcid":false,"given":"Gary","family":"Boudreau","sequence":"additional","affiliation":[{"name":"Ericsson Canada, Ottawa, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5253-2429","authenticated-orcid":false,"given":"Ali","family":"Afana","sequence":"additional","affiliation":[{"name":"Ericsson Canada, Ottawa, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229086"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1429274"},{"key":"ref5","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Intel. Conf. Artif. Intell. Statist. (AISTATS)","author":"McMahan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486403"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref8","first-page":"1","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","author":"Alistarh"},{"key":"ref9","first-page":"5325","article-title":"Error compensated quantized SGD and its applications to large-scale distributed optimization","volume-title":"Proc. Intel. Conf. Mach. Learn. (ICML)","author":"Wu"},{"key":"ref10","first-page":"4035","article-title":"ZipML: Training linear models with end-to-end low precision, and a little bit of deep learning","volume-title":"Proc. Intel. Conf. Mach. Learn. (ICML)","volume":"70","author":"Zhang"},{"key":"ref11","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","volume":"30","author":"Wen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-354"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734719"},{"key":"ref15","first-page":"2530","article-title":"A linear speedup analysis of distributed deep learning with sparse and quantized communication","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","volume":"31","author":"Jiang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2019.8815453"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3103920"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084806"},{"key":"ref19","first-page":"1","article-title":"Scalecom: Scalable sparsified gradient compression for communication-efficient distributed training","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","volume":"33","author":"Chen"},{"key":"ref20","first-page":"1","article-title":"Communication-efficient distributed learning via lazily aggregated quantized gradients","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","volume":"32","author":"Sun"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2010.01.001"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3394498"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.05.006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2161027"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426639"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760092"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2743462"},{"issue":"2","key":"ref32","first-page":"1000","article-title":"Communication-efficient distributed optimization using an approximate Newton-type method","volume-title":"Proc. Intel. Conf. Mach. Learn. (ICML)","volume":"32","author":"Shamir"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2254478"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2916985"},{"key":"ref35","first-page":"3068","article-title":"Communication-efficient distributed dual coordinate ascent","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","volume":"27","author":"Jaggi"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488818"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796860"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3318474"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7526804"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2755720"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3057601"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2999671"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF53345.2021.9723285"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3185897"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79995-2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1955.1055126"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1976.1055508"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1973.1055037"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2002.808103"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2007.895188"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-322-2292-7"},{"key":"ref53","first-page":"1","article-title":"Online convex optimization with stochastic constraints","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","volume":"30","author":"Yu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2827302"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3410048.3410051"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3188285"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3194357"},{"key":"ref58","first-page":"1","article-title":"A low complexity algorithm with O(\u221aT) regret and O(1) constraint violations for online convex optimization with long term constraints","volume":"21","author":"Yu","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref59","first-page":"2503","article-title":"Trading regret for efficiency: Online convex optimization with long term constraints","volume":"13","author":"Mahdavi","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2890368"},{"key":"ref61","first-page":"3750","article-title":"SGD and hogwild! Convergence without the bounded gradients assumption","volume-title":"Proc. Intel. Conf. Mach. Learn. (ICML)","author":"Nguyen"},{"key":"ref62","first-page":"1","article-title":"Improved dynamic regret for non-degenerate functions","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","volume":"30","author":"Zhang"},{"key":"ref63","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Intel. Conf. Mach. Learn. (ICML)","author":"Karimireddy"},{"key":"ref64","first-page":"14606","article-title":"Linear convergence in federated learning: Tackling client heterogeneity and sparse gradients","volume-title":"Proc. Adv. Neural Info. Proc. Sys. (NeurIPS)","volume":"34","author":"Mitra"},{"key":"ref65","volume-title":"The MNIST Database","author":"LeCun","year":"1998"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11039001\/10849650.pdf?arnumber=10849650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:37:47Z","timestamp":1750268267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":65,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3530460","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}