{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T03:31:14Z","timestamp":1784086274234,"version":"3.55.0"},"reference-count":58,"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":"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\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FL-170100117"],"award-info":[{"award-number":["FL-170100117"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3300886","type":"journal-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T18:09:12Z","timestamp":1690913352000},"page":"14453-14464","source":"Crossref","is-referenced-by-count":26,"title":["Efficient Federated Learning Via Local Adaptive Amended Optimizer With Linear Speedup"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2271-252X","authenticated-orcid":false,"given":"Yan","family":"Sun","sequence":"first","affiliation":[{"name":"University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4645-2999","authenticated-orcid":false,"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8976-2084","authenticated-orcid":false,"given":"Liang","family":"Ding","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"6654","article-title":"Quasi-global momentum: Accelerating decentralized deep learning on heterogeneous data","author":"lin","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01198-w"},{"key":"ref12","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","author":"karimireddy","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","author":"yang","year":"2021","journal-title":"Proc 9th Int Conf Learn Representations"},{"key":"ref14","article-title":"FedCM: Federated learning with client-level momentum","author":"xu","year":"2021"},{"key":"ref58","first-page":"4387","article-title":"The non-IID data quagmire of decentralized machine learning","author":"hsieh","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3412815.3416891"},{"key":"ref52","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2018","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref11","article-title":"Fed-LAMB: Layerwise and dimensionwise locally adaptive optimization algorithm","author":"karimi","year":"2021"},{"key":"ref55","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"hsu","year":"2019"},{"key":"ref10","article-title":"Local AdaAlter: Communication-efficient stochastic gradient descent with adaptive learning rates","author":"xie","year":"2019"},{"key":"ref54","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref17","article-title":"Don't use large mini-batches, use local SGD","author":"lin","year":"2020","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref16","article-title":"On the convergence of FedAvg on non-IID data","author":"li","year":"2020","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref19","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst 26 27th Annu Conf Neural Inf Process Syst"},{"key":"ref18","first-page":"429","article-title":"Federated optimization in heterogeneous networks","author":"li","year":"2020","journal-title":"Proc Mach Learn Syst"},{"key":"ref51","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012"},{"key":"ref50","article-title":"Global convergence of adaptive gradient methods for an over-parameterized neural network","author":"wu","year":"2019"},{"key":"ref46","first-page":"4617","article-title":"Distributed second order methods with fast rates and compressed communication","author":"islamov","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref45","article-title":"FedNL: Making Newton-type methods applicable to federated learning","author":"safaryan","year":"2021"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref47","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":"ref42","article-title":"Towards practical Adam: Non-convexity, convergence theory, and mini-batch acceleration","author":"chen","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3470890"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00984"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467309"},{"key":"ref49","first-page":"983","article-title":"On the convergence of stochastic gradient descent with adaptive stepsizes","author":"li","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9517850"},{"key":"ref7","article-title":"Federated learning based on dynamic regularization","author":"acar","year":"2021","journal-title":"Proc 9th Int Conf Learn Representations"},{"key":"ref9","article-title":"Adaptive federated optimization","author":"reddi","year":"2021","journal-title":"Proc 9th Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref6","article-title":"SlowMo: Improving communication-efficient distributed SGD with slow momentum","author":"wang","year":"2020","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref5","article-title":"Local SGD converges fast and communicates little","author":"stich","year":"2019","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01138"},{"key":"ref35","first-page":"244","article-title":"Adaptive bound optimization for online convex optimization","author":"mcmahan","year":"2010","journal-title":"Proc 23rd Conf Learn Theory"},{"key":"ref34","first-page":"9489","article-title":"Personalized federated learning using hypernetworks","author":"shamsian","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref37","first-page":"613","article-title":"CADA: Communication-adaptive distributed Adam","author":"chen","year":"2021","journal-title":"Proc 24th Int Conf Artif Intell Statist"},{"key":"ref36","article-title":"On the convergence of adaptive gradient methods for nonconvex optimization","author":"zhou","year":"2018"},{"key":"ref31","article-title":"Federated learning with randomized Douglas-Rachford splitting methods","author":"pham","year":"2021"},{"key":"ref30","article-title":"FedSplit: An algorithmic framework for fast federated optimization","author":"pathak","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst 33 Annu Conf Neural Inf Process Syst"},{"key":"ref33","first-page":"5113","article-title":"Collaborative channel pruning for deep networks","author":"peng","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref32","article-title":"FedMGDA: Federated learning meets multi-objective optimization","author":"hu","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc 20th Int Conf Artif Intell Statist"},{"key":"ref39","article-title":"Local adaptivity in federated learning: Convergence and consistency","author":"wang","year":"2021"},{"key":"ref38","article-title":"Effective federated adaptive gradient methods with non-IID decentralized data","author":"tong","year":"2020"},{"key":"ref24","first-page":"6692","article-title":"From local SGD to local fixed-point methods for federated learning","author":"malinovskiy","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref23","article-title":"Federated learning of a mixture of global and local models","author":"hanzely","year":"2020"},{"key":"ref26","article-title":"Local SGD with a communication overhead depending only on the number of workers","author":"spiridonoff","year":"2006"},{"key":"ref25","first-page":"4762","article-title":"History-gradient aided batch size adaptation for variance reduced algorithms","author":"ji","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref20","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","author":"wang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst 33 Annu Conf Neural Inf Process Syst"},{"key":"ref22","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","author":"yu","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3115952"},{"key":"ref28","first-page":"10334","article-title":"Is local SGD better than minibatch SGD?","author":"woodworth","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref27","article-title":"First analysis of local GD on heterogeneous data","author":"khaled","year":"2019"},{"key":"ref29","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","author":"yurochkin","year":"2019","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10201382.pdf?arnumber=10201382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:52:33Z","timestamp":1701114753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10201382\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":58,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3300886","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}