{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:18:03Z","timestamp":1740169083680,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702539","60970034","61105050"],"award-info":[{"award-number":["61702539","60970034","61105050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2814212","type":"journal-article","created":{"date-parts":[[2018,3,19]],"date-time":"2018-03-19T21:47:08Z","timestamp":1521496028000},"page":"16165-16175","source":"Crossref","is-referenced-by-count":4,"title":["Analysis of the Variance Reduction in SVRG and a New Acceleration Method"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1972-6608","authenticated-orcid":false,"given":"Erxue","family":"Min","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianjing","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"journal-title":"Fast and simple PCA via convex optimization","year":"2015","author":"garber","key":"ref31"},{"key":"ref30","first-page":"747","article-title":"SDCA without duality, regularization, and individual convexity","author":"shalev-shwartz","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"Variants of RMSProp and Adagrad with logarithmic regret bounds","year":"2017","author":"mukkamala","key":"ref36"},{"journal-title":"ADADELTA An Adaptive Learning Rate Method","year":"2012","author":"zeiler","key":"ref35"},{"key":"ref34","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":"ref10","first-page":"1","article-title":"Stochastic variance reduced optimization for nonconvex sparse learning","author":"li","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","first-page":"1990","article-title":"Adaptive variance reducing for stochastic gradient descent","author":"shen","year":"2016","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/140961791"},{"key":"ref13","first-page":"1080","article-title":"Improved SVRG for non-strongly-convex or sum-of-non-convex objectives","author":"allen-zhu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","first-page":"2251","article-title":"StopWasting my gradients: Practical SVRG","author":"babanezhad","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"Katyusha Accelerated variance reduction for faster SGD","year":"2016","author":"allen-zhu","key":"ref15"},{"key":"ref16","first-page":"685","article-title":"Barzilai–Borwein step size for stochastic gradient descent","author":"tan","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966219"},{"key":"ref18","first-page":"2323","article-title":"Asynchronous distributed semi-stochastic gradient optimization","author":"zhang","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"journal-title":"Asynchronous stochastic gradient descent with variance reduction for non-convex optimization","year":"2016","author":"huo","key":"ref19"},{"key":"ref28","first-page":"699","article-title":"Variance reduction for faster non-Convex optimization","author":"allen-zhu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"journal-title":"Nonconvex sparse learning via stochastic optimization with progressive variance reduction","year":"2016","author":"li","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2955102"},{"key":"ref6","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"},{"journal-title":"Trading-off variance and complexity in stochastic gradient descent","year":"2016","author":"shah","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/JSTSP.2015.2505682","article-title":"Mini-batch semi-stochastic gradient descent in the proximal setting","volume":"10","author":"kone?n\u00fd","year":"2016","journal-title":"IEEE J Sel Topics Signal Process"},{"journal-title":"Semi-stochastic gradient descent methods","year":"2013","author":"kone?n\u00fd","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref9","first-page":"980","article-title":"Linear convergence with condition number independent access of full gradients","author":"zhang","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref20","first-page":"794","article-title":"Parallel asynchronous stochastic variance reduction for nonconvex optimization","author":"fang","year":"2017","journal-title":"Proc AAAI"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.11.044"},{"key":"ref21","first-page":"4404","article-title":"Distributed stochastic variance reduced gradient methods by sampling extra data with replacement","volume":"18","author":"lee","year":"2017","journal-title":"J Mach Learn Res"},{"journal-title":"Linear convergence of accelerated stochastic gradient descent for nonconvex nonsmooth optimization","year":"2017","author":"huang","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0022"},{"journal-title":"Stochastic variance reduction gradient for a non-convex problem using graduated optimization","year":"2017","author":"chen","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2016.7852377"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08319495.pdf?arnumber=8319495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:16:12Z","timestamp":1642004172000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8319495\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2814212","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2018]]}}}