{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T17:09:04Z","timestamp":1779296944600,"version":"3.51.4"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876095"],"award-info":[{"award-number":["61876095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61751308"],"award-info":[{"award-number":["61751308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673179"],"award-info":[{"award-number":["61673179"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002663","name":"Northwestern Polytechnical University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/tnnls.2019.2891088","type":"journal-article","created":{"date-parts":[[2019,1,25]],"date-time":"2019-01-25T20:06:32Z","timestamp":1548446792000},"page":"3338-3346","source":"Crossref","is-referenced-by-count":42,"title":["An Accelerated Linearly Convergent Stochastic L-BFGS Algorithm"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8798-9322","authenticated-orcid":false,"given":"Daqing","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7069-3752","authenticated-orcid":false,"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8088-367X","authenticated-orcid":false,"given":"Changshui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"allen-zhu","year":"2016","journal-title":"Katyusha The first direct acceleration of stochastic gradient methods"},{"key":"ref38","author":"allen-zhu","year":"2014","journal-title":"Linear coupling An ultimate unification of gradient and mirror descent"},{"key":"ref33","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":"ref32","author":"gong","year":"2014","journal-title":"Linear convergence of variance-reduced stochastic gradient without strong convexity"},{"key":"ref31","first-page":"2251","article-title":"StopWasting my gradients: Practical SVRG","author":"harikandeh","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","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?","year":"2016","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref37","first-page":"3384","article-title":"A universal catalyst for first-order optimization","author":"lin","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-014-0839-0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0629-5"},{"key":"ref34","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate o (1\/k2)","volume":"27","author":"nesterov","year":"1983","journal-title":"Soviet Math Doklady"},{"key":"ref10","first-page":"1646","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","author":"defazio","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref40","first-page":"7","author":"wright","year":"1999","journal-title":"Numerical Optimization"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1030-6"},{"key":"ref12","first-page":"436","article-title":"A stochastic quasi-Newton method for online convex optimization","author":"schraudolph","year":"2007","journal-title":"Proc 11th Int Conf Artif Intell Statist"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/140954362"},{"key":"ref14","first-page":"1869","article-title":"Stochastic block BFGS: Squeezing more curvature out of data","author":"gower","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn"},{"key":"ref15","first-page":"249","article-title":"A linearly-convergent stochastic L-BFGS algorithm","author":"moritz","year":"2016","journal-title":"Proc 19th Int Conf Artif Intell"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2784360"},{"key":"ref18","first-page":"2597","article-title":"A superlinearly-convergent proximal Newton-type method for the optimization of finite sums","author":"rodomanov","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/17M1122943"},{"key":"ref28","author":"kiros","year":"2013","journal-title":"Training neural networks with stochastic Hessian-free optimization"},{"key":"ref4","first-page":"53","article-title":"Some global convergence properties of a variable metric algorithm for minimization without exact line searches","volume":"9","author":"powell","year":"1976","journal-title":"Nonlinear Prog"},{"key":"ref27","first-page":"1033","article-title":"Learning recurrent neural networks with hessian-free optimization","author":"martens","year":"2011","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1974-0343581-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/140961791"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/0724077"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015332"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref9","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"2013","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref20","volume":"87","author":"nesterov","year":"2013","journal-title":"Introductory Lectures on Convex Optimization A Basic Course"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2383395"},{"key":"ref21","first-page":"1574","article-title":"Stochastic proximal gradient descent with acceleration techniques","author":"nitanda","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","first-page":"2510","article-title":"A differential equation for modeling nesterov’s accelerated gradient method: Theory and insights","author":"su","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2357775"},{"key":"ref23","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":"ref26","first-page":"735","article-title":"Deep learning via Hessian-free optimization","author":"martens","year":"2010","journal-title":"Proc 27th Int Conf Int Conf Mach Learn"},{"key":"ref25","first-page":"2933","article-title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","author":"dauphin","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8886738\/08626766.pdf?arnumber=8626766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:14:41Z","timestamp":1657746881000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8626766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":42,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2891088","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}