{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:15:49Z","timestamp":1780589749918,"version":"3.54.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["CCF-2007668"],"award-info":[{"award-number":["CCF-2007668"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tsp.2020.3033354","type":"journal-article","created":{"date-parts":[[2020,10,26]],"date-time":"2020-10-26T20:01:17Z","timestamp":1603742477000},"page":"6287-6302","source":"Crossref","is-referenced-by-count":11,"title":["High-Dimensional Nonconvex Stochastic Optimization by Doubly Stochastic Successive Convex Approximation"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6603-0091","authenticated-orcid":false,"given":"Aryan","family":"Mokhtari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2447-2873","authenticated-orcid":false,"given":"Alec","family":"Koppel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2449255"},{"key":"ref38","first-page":"285","article-title":"An asynchronous parallel stochastic coordinate descent algorithm","volume":"16","author":"liu","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/120887679"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00939948"},{"key":"ref31","first-page":"1965","article-title":"DAve-QN: A distributed averaged quasi-Newton method with local superlinear convergence rate","author":"soori","year":"2020","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/17M1122943"},{"key":"ref37","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"1","volume":"156","author":"richt\u00e1rik","year":"2015","journal-title":"Math Program"},{"key":"ref35","first-page":"1","article-title":"On the complexity analysis of randomized block-coordinate descent methods","volume":"152","author":"lu","year":"2013","journal-title":"Math Program"},{"key":"ref34","first-page":"28","article-title":"Feature clustering for accelerating parallel coordinate descent","author":"scherrer","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2357775"},{"key":"ref27","first-page":"1646","article-title":"Saga: A fast incremental gradient method with support for non-strongly convex composite objectives","author":"defazio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","first-page":"3151","article-title":"Global convergence of online limited memory BFGS","volume":"16","author":"mokhtari","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461449"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953048"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2293126"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7526120"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2399858"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1030-6"},{"key":"ref25","first-page":"378","article-title":"Accelerated mini-batch stochastic dual coordinate ascent","author":"shalev-shwartz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881969"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-1904-8"},{"key":"ref55","first-page":"1","article-title":"Stochastic conditional gradient methods: From convex minimization to submodular maximization","volume":"21","author":"mokhtari","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref54","article-title":"Adaptive signal processing algorithms: Stability and performance","author":"solo","year":"1994"},{"key":"ref53","first-page":"19","article-title":"Online learning for matrix factorization and sparse coding","volume":"11","author":"mairal","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref52","author":"mallat","year":"2009","journal-title":"A Wavelet Tour of Signal Processing The Sparse Way"},{"key":"ref10","first-page":"2635","article-title":"Learnability, stability and uniform convergence","volume":"11","author":"shalev-shwartz","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2307\/1390712"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2016.2524588"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017501703105"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541725"},{"key":"ref16","article-title":"Symmetry, saddle points, and global geometry of nonconvex matrix factorization","author":"li","year":"2016","journal-title":"arXiv 1612 09296"},{"key":"ref17","first-page":"797","article-title":"Escaping from saddle points–online stochastic gradient for tensor decomposition","author":"ge","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177011077"},{"key":"ref19","first-page":"1","article-title":"Efficient large-scale gaussian process bandits by believing only informative actions","volume":"120","author":"bedi","year":"0","journal-title":"Proc 2nd Annu Conf Learn Dyn Control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.156"},{"key":"ref3","author":"vapnik","year":"1999","journal-title":"The Nature of Statistical Learning Theory"},{"key":"ref6","first-page":"265","article-title":"On optimization methods for deep learning","author":"ngiam","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2017.2662618"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.79"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1109\/JSTSP.2007.910281","article-title":"Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems","volume":"1","author":"nowak","year":"2007","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21236\/ADA478437"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref46","article-title":"Introduction to optimization","volume":"1","author":"polyak","year":"1987"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1017-3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-015-0150-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2531627"},{"key":"ref41","article-title":"Convergence rate of distributed optimization algorithms based on gradient tracking","author":"sun","year":"2019","journal-title":"arXiv 1905 02637"},{"key":"ref44","first-page":"1","article-title":"A class of parallel doubly stochastic algorithms for large-scale learning","volume":"21","author":"mokhtari","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/140961791"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/78\/8933520\/9239907-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/8933520\/09239907.pdf?arnumber=9239907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:40:45Z","timestamp":1651070445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9239907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tsp.2020.3033354","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}