{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:07:47Z","timestamp":1784131667774,"version":"3.55.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2419982"],"award-info":[{"award-number":["2419982"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2342253"],"award-info":[{"award-number":["2342253"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2236483"],"award-info":[{"award-number":["2236483"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2330154"],"award-info":[{"award-number":["2330154"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/ton.2025.3552423","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T13:53:32Z","timestamp":1744206812000},"page":"2036-2048","source":"Crossref","is-referenced-by-count":3,"title":["Robust Decentralized Learning With Local Updates and Gradient Tracking"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3834-7418","authenticated-orcid":false,"given":"Sajjad","family":"Ghiasvand","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1730-8402","authenticated-orcid":false,"given":"Amirhossein","family":"Reisizadeh","sequence":"additional","affiliation":[{"name":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3369-3846","authenticated-orcid":false,"given":"Mahnoosh","family":"Alizadeh","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1126-0292","authenticated-orcid":false,"given":"Ramtin","family":"Pedarsani","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton63246.2024.10735328"},{"key":"ref2","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u00fd","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.04.009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom60117.2023.00043"},{"key":"ref6","article-title":"Training-free mitigation of adversarial attacks on deep learning-based MRI reconstruction","author":"Saberi","year":"2025","journal-title":"arXiv:2501.01908"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2022.3182355"},{"key":"ref8","first-page":"21554","article-title":"Robust federated learning: The case of affine distribution shifts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Reisizadeh"},{"key":"ref9","first-page":"4387","article-title":"The non-iid data quagmire of decentralized machine learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hsieh"},{"key":"ref10","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3328632"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3324257"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3316421"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3390416"},{"key":"ref15","first-page":"11422","article-title":"An improved analysis of gradient tracking for decentralized machine learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Koloskova"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01487-0"},{"key":"ref17","article-title":"Decentralized stochastic gradient tracking for non-convex empirical risk minimization","author":"Zhang","year":"2019","journal-title":"arXiv:1909.02712"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ACC60939.2024.10644388"},{"key":"ref19","first-page":"1594","article-title":"Communication efficient primal-dual algorithm for nonconvex nonsmooth distributed optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/20M134842X"},{"key":"ref21","first-page":"18342","article-title":"Optimal and practical algorithms for smooth and strongly convex decentralized optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kovalev"},{"key":"ref22","first-page":"1","article-title":"Communication-efficient distributed optimization in networks with gradient tracking and variance reduction","volume":"21","author":"Li","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/21M1450677"},{"issue":"222","key":"ref24","first-page":"1","article-title":"Variance reduced EXTRA and DIGing and their optimal acceleration for strongly convex decentralized optimization","volume":"23","author":"Li","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","first-page":"9217","article-title":"Improving the sample and communication complexity for decentralized non-convex optimization: Joint gradient estimation and tracking","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Sun"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ITA50056.2020.9244951"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3097211"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/20M1361158"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3329005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2024.2322095"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383873"},{"key":"ref32","first-page":"2350","article-title":"Federated learning with compression: Unified analysis and sharp guarantees","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Haddadpour"},{"key":"ref33","article-title":"Balancing communication and computation in gradient tracking algorithms for decentralized optimization","author":"Berahas","year":"2023","journal-title":"arXiv:2303.14289"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-40442-0_9"},{"key":"ref35","first-page":"6083","article-title":"On gradient descent ascent for nonconvex-concave minimax problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref36","article-title":"Single-timescale stochastic nonconvex-concave optimization for smooth nonlinear TD learning","author":"Qiu","year":"2020","journal-title":"arXiv:2008.10103"},{"key":"ref37","first-page":"20566","article-title":"Stochastic recursive gradient descent ascent for stochastic Nonconvex-strongly-concave minimax problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Luo"},{"key":"ref38","first-page":"482","article-title":"The complexity of nonconvex-strongly-concave minimax optimization","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2449255"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7403075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2023.2280062"},{"key":"ref42","first-page":"8172","article-title":"Distributed saddle-point problems under data similarity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Beznosikov"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-91059-4_18"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26234"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3565287.3610267"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/23m1558677"},{"key":"ref47","article-title":"Decentralized stochastic gradient descent ascent for finite-sum minimax problems","author":"Gao","year":"2022","journal-title":"arXiv:2212.02724"},{"key":"ref48","article-title":"Variance-reduced accelerated methods for decentralized stochastic double-regularized nonconvex strongly-concave minimax problems","author":"Mancino-Ball","year":"2023","journal-title":"arXiv:2307.07113"},{"key":"ref49","article-title":"An efficient stochastic algorithm for decentralized nonconvex-strongly-concave minimax optimization","author":"Chen","year":"2022","journal-title":"arXiv:2212.02387"},{"key":"ref50","first-page":"25865","article-title":"A faster decentralized algorithm for nonconvex minimax problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xian"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30076"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054056"},{"key":"ref53","first-page":"11056","article-title":"A decentralized parallel algorithm for training generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref54","first-page":"15236","article-title":"Momentum-based variance reduction in non-convex SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cutkosky"},{"key":"ref55","first-page":"689","article-title":"SPIDER: Near-optimal non-convex optimization via stochastic path-integrated differential estimator","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Fang"},{"key":"ref56","article-title":"Efficient algorithms for federated saddle point optimization","author":"Hou","year":"2021","journal-title":"arXiv:2102.06333"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06239-z"},{"key":"ref58","first-page":"6060","article-title":"A communication-efficient algorithm with linear convergence for federated minimax learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref59","first-page":"15111","article-title":"Distributionally robust federated averaging","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref60","first-page":"1387","article-title":"Local stochastic gradient descent ascent: Convergence analysis and communication efficiency","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Deng"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26246"},{"key":"ref62","first-page":"19683","article-title":"Federated minimax optimization: Improved convergence analyses and algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sharma"},{"key":"ref63","article-title":"Federated minimax optimization with client heterogeneity","author":"Sharma","year":"2023","journal-title":"arXiv:2302.04249"},{"key":"ref64","first-page":"7142","article-title":"SAGDA: Achieving o (\u03b5-2) communication complexity in federated min-max learning","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097188"},{"key":"ref67","first-page":"2738","article-title":"Near-optimal algorithms for minimax optimization","volume-title":"Proc. Conf. Learn. Theory","author":"Lin"},{"key":"ref68","first-page":"5381","article-title":"A unified theory of decentralized SGD with changing topology and local updates","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Koloskova"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref70","article-title":"Robust decentralized learning with local updates and gradient tracking","author":"Ghiasvand","year":"2024","journal-title":"arXiv:2405.00965"},{"key":"ref71","first-page":"18825","article-title":"Taming communication and sample complexities in decentralized policy evaluation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref73","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref74","article-title":"Adversarial machine learning at scale","author":"Kurakin","year":"2016","journal-title":"arXiv:1611.01236"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00503"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6017"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/10723154\/11131549\/10959108-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11131549\/10959108.pdf?arnumber=10959108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:12Z","timestamp":1755910332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10959108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":76,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3552423","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}