{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T01:15:33Z","timestamp":1790385333372,"version":"4.1.0"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000142012394"],"award-info":[{"award-number":["N000142012394"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office (ARO) Multidisciplinary University Research Initiatives (MURI) program","doi-asserted-by":"publisher","award":["W911NF-19-1-0217"],"award-info":[{"award-number":["W911NF-19-1-0217"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation (NSF) Transdisciplinary Research In Principles Of Data Science (TRIPODS) under the Foundations of Data Science Institute"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tit.2023.3317168","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T13:54:20Z","timestamp":1695131660000},"page":"7836-7866","source":"Crossref","is-referenced-by-count":13,"title":["Federated Optimization of Smooth Loss Functions"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1122-3069","authenticated-orcid":false,"given":"Ali","family":"Jadbabaie","sequence":"first","affiliation":[{"name":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-8116","authenticated-orcid":false,"given":"Anuran","family":"Makur","sequence":"additional","affiliation":[{"name":"Department of Computer Science and the Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0737-3259","authenticated-orcid":false,"given":"Devavrat","family":"Shah","sequence":"additional","affiliation":[{"name":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/110830629"},{"issue":"16","key":"ref6","article-title":"First-order methods with inexact oracle: The strongly convex case","volume":"2013","author":"Devolder","year":"2013","journal-title":"CORE Discuss. Papers"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2017.1296439"},{"key":"ref8","first-page":"1","article-title":"Convergence rates of inexact proximal-gradient methods for convex optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Schmidt"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"issue":"3","key":"ref11","first-page":"543","article-title":"A method of solving a convex programming problem with convergence rate O(1\/k2)","volume":"269","author":"Nesterov","year":"1983","journal-title":"Doklady Akademii Nauk SSSR"},{"key":"ref12","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":"ref13","first-page":"1","article-title":"A stochastic gradient method with an exponential convergence rate for finite training sets","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Le Roux"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1030-6"},{"key":"ref15","first-page":"567","article-title":"Stochastic dual coordinate ascent methods for regularized loss minimization","volume":"14","author":"Shalev-Shwartz","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Johnson"},{"key":"ref17","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","author":"Tieleman","year":"2012"},{"key":"ref19","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/2200000058"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s41745-019-0098-4"},{"key":"ref23","article-title":"Gradient-based empirical risk minimization using local polynomial regression","author":"Jadbabaie","year":"2020","journal-title":"arXiv:2011.02522"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7566-5"},{"key":"ref25","volume-title":"Local Polynomial Modeling and Its Applications","volume":"66","author":"Fan","year":"1996"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-48425-4_2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/b13794"},{"key":"ref28","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"McMahan"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref30","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Reisizadeh"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/jsait.2022.3205475"},{"key":"ref32","article-title":"Faster on-device training using new federated momentum algorithm","author":"Huo","year":"2020","journal-title":"arXiv:2002.02090v1"},{"key":"ref33","article-title":"Cooperative SGD: A unified framework for the design and analysis of communication-efficient SGD algorithms","author":"Wang","year":"2019","journal-title":"arXiv:1808.07576v3"},{"key":"ref34","first-page":"7057","article-title":"FedSplit: An algorithmic framework for fast federated optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Pathak"},{"key":"ref35","first-page":"10946","article-title":"Federated learning with only positive labels","volume-title":"Proc. 37th Annu. Int. Conf. Mach. Learn. (ICML)","author":"Yu"},{"key":"ref36","first-page":"1","article-title":"Adaptive federated optimization","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Reddi"},{"key":"ref37","article-title":"One-shot federated learning","author":"Guha","year":"2019","journal-title":"arXiv:1902.11175v2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CISS56502.2023.10089643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CISS53076.2022.9751161"},{"key":"ref40","article-title":"Federated learning with server learning: Enhancing performance for non-IID data","author":"Sy Mai","year":"2023","journal-title":"arXiv:2210.02614v3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1214\/14-AOS1272"},{"key":"ref42","first-page":"5433","article-title":"Rates of convergence of spectral methods for graphon estimation","volume-title":"Proc. 35th Annu. Int. Conf. Mach. Learn. (ICML)","author":"Xu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2021.1928513"},{"key":"ref44","volume-title":"The MNIST Database Of Handwritten Digits","author":"LeCun","year":"2021"},{"key":"ref45","volume-title":"The CIFAR-10 Dataset","author":"Krizhevsky","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1561\/2200000064"},{"key":"ref47","volume-title":"Statistical methods for machine learning","author":"Wasserman","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/1109020"},{"issue":"4","key":"ref49","first-page":"359","article-title":"Smooth regression analysis","volume":"26","author":"Watson","year":"1964","journal-title":"S\u0101nkhy\u0101, Indian J. Statist. A"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1037\/e471672008-001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107049949"},{"key":"ref53","volume-title":"Fourier Analysis: An Introduction","volume":"1","author":"Stein","year":"2003"},{"key":"ref54","volume-title":"Complex Analysis","volume":"2","author":"Stein","year":"2003"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2009.2035722"},{"key":"ref56","article-title":"Sample efficient reinforcement learning via low-rank matrix estimation","author":"Shah","year":"2020","journal-title":"arXiv:2006.06135"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1215\/S0012-7094-75-04256-8"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176347004"},{"key":"ref59","first-page":"122","article-title":"Efficient low-rank stochastic gradient descent methods for solving semidefinite programs","volume-title":"Proc. 17th Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Chen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1137\/130916138"},{"key":"ref61","article-title":"Gradient descent happens in a tiny subspace","author":"Gur-Ari","year":"2018","journal-title":"arXiv:1812.04754"},{"key":"ref62","first-page":"1","article-title":"Empirical analysis of the Hessian of over-parametrized neural networks","volume-title":"Proc. 6th Int. Conf. Learn. Represent. Workshop (ICLR)","author":"Sagun"},{"key":"ref63","article-title":"The full spectrum of deepnet Hessians at scale: Dynamics with SGD training and sample size","author":"Papyan","year":"2019","journal-title":"arXiv:1811.07062v2"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1137\/19M1296070"},{"key":"ref65","article-title":"Dissecting Hessian: Understanding common structure of Hessian in neural networks","author":"Wu","year":"2021","journal-title":"arXiv:2010.04261v5"},{"key":"ref66","first-page":"23914","article-title":"Analytic insights into structure and rank of neural network Hessian maps","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Singh"},{"key":"ref67","first-page":"1","article-title":"Training invariances and the low-rank phenomenon: Beyond linear networks","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Le"},{"key":"ref68","article-title":"SGD and weight decay provably induce a low-rank bias in neural networks","author":"Galanti","year":"2023","journal-title":"arXiv:2206.05794v3"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2015509117"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2103091118"},{"key":"ref71","article-title":"Limitations of neural collapse for understanding generalization in deep learning","author":"Hui","year":"2022","journal-title":"arXiv:2202.08384"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053036"},{"issue":"9","key":"ref73","first-page":"1","article-title":"Random design analysis of ridge regression","volume-title":"Proc. 25th Annu. Conf. Learn. Theory (COLT), Proc. Mach. Learn. Res. (PMLR)","volume":"23","author":"Hsu"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1515\/9781400835560"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1561\/2000000050"},{"key":"ref76","volume-title":"Problem Complexity and Method Efficiency in Optimization","author":"Nemirovsky","year":"1983"},{"key":"ref77","first-page":"1","article-title":"Graph oracle models, lower bounds, and gaps for parallel stochastic optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Woodworth"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3176253"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2880407"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2736066"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139626514"},{"key":"ref82","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-33483-2","volume-title":"Modelling Extremal Events for Insurance and Finance","volume":"33","author":"Embrechts","year":"1997"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref84","article-title":"Rates of convergence of spectral methods for graphon estimation","author":"Xu","year":"2017","journal-title":"arXiv:1709.03183"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/0047-259X(81)90099-3"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asx042"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9781139020411"},{"key":"ref88","volume-title":"Mathematical Analysis","author":"Apostol","year":"1974"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907369117"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1002\/rsa.10073"},{"key":"ref91","volume-title":"Information-theoretic methods for high-dimensional statistics","author":"Wu","year":"2020"},{"key":"ref92","volume-title":"An Introduction to Probability Theory and Its Applications","volume":"1","author":"Feller","year":"1968"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2011.84"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.2307\/3619777"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1017\/S0025557200179598"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/10328924\/10255658-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/10328924\/10255658.pdf?arnumber=10255658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:49:11Z","timestamp":1760982551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10255658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":95,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tit.2023.3317168","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}