{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T01:43:49Z","timestamp":1782870229151,"version":"3.54.5"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFB0204300"],"award-info":[{"award-number":["2018YFB0204300"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61932001"],"award-info":[{"award-number":["61932001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61906200"],"award-info":[{"award-number":["61906200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2020.3038535","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T21:29:20Z","timestamp":1606339760000},"page":"1044-1056","source":"Crossref","is-referenced-by-count":17,"title":["Novel Convergence Results of Adaptive Stochastic Gradient Descents"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5024-1900","authenticated-orcid":false,"given":"Tao","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8285-2738","authenticated-orcid":false,"given":"Linbo","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1012-5301","authenticated-orcid":false,"given":"Qing","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9743-2034","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-018-09409-5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0701-9"},{"key":"ref33","first-page":"643","article-title":"Gradient methods for minimizing functionals","volume":"3","author":"polyak","year":"1963","journal-title":"Zhurnal Vychislitel’noi Matematiki i Matematicheskoi Fiziki"},{"key":"ref32","first-page":"8745","article-title":"Uniform convergence of gradients for non-convex learning and optimization","author":"foster","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"314","article-title":"Stochastic variance reduction for nonconvex optimization","author":"reddi","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1100.0449"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-007-0133-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-09-05048-X"},{"key":"ref34","first-page":"87","article-title":"A topological property of real analytic subsets","volume":"117","author":"lojasiewicz","year":"1963","journal-title":"Coll du CNRS Les équations aux dérivées Partielles"},{"key":"ref28","first-page":"9793","article-title":"Adaptive methods for nonconvex optimization","author":"zaheer","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","article-title":"Escaping saddle points with adaptive gradient methods","author":"staib","year":"2019","journal-title":"arXiv 1901 09149"},{"key":"ref29","article-title":"Convergence and dynamical behavior of the ADAM algorithm for non-convex stochastic optimization","author":"barakat","year":"2018","journal-title":"arXiv 1810 02263"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref20","article-title":"AdaGrad stepsizes: Sharp convergence over nonconvex landscapes, from any initialization","author":"ward","year":"2018","journal-title":"arXiv 1806 01811"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01138"},{"key":"ref21","first-page":"1","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2019","journal-title":"Proc ICLR"},{"key":"ref24","first-page":"1","article-title":"On the convergence of a class of Adam-type algorithms for non-convex optimization","author":"chen","year":"2018","journal-title":"Proc ICLR"},{"key":"ref23","article-title":"Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration","author":"de","year":"2018","journal-title":"arXiv 1807 06766"},{"key":"ref26","article-title":"Global convergence of adaptive gradient methods for an over-parameterized neural network","author":"wu","year":"2019","journal-title":"arXiv 1902 07111"},{"key":"ref25","article-title":"On the convergence of adaptive gradient methods for nonconvex optimization","author":"zhou","year":"2018","journal-title":"arXiv 1808 05671"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11075-018-0565-4"},{"key":"ref10","article-title":"Lecture 6.5-rmsprop, coursera: Neural networks for machine learning","author":"tieleman","year":"2012"},{"key":"ref11","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref40","article-title":"An inertial Newton algorithm for deep learning","author":"castera","year":"2019","journal-title":"arXiv 1905 12278"},{"key":"ref12","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref13","article-title":"Incorporating Nesterov momentum into Adam","author":"dozat","year":"2016","journal-title":"Proc ICLR Workshop"},{"key":"ref14","first-page":"4148","article-title":"The marginal value of adaptive gradient methods in machine learning","author":"wilson","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","article-title":"Padam: Closing the generalization gap of adaptive gradient methods in training deep neural networks","author":"chen","year":"2018","journal-title":"arXiv 1806 06763"},{"key":"ref16","first-page":"3262","article-title":"Riemannian adaptive stochastic gradient algorithms on matrix manifolds","author":"kasai","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"2019","journal-title":"arXiv 1902 09843"},{"key":"ref18","article-title":"Weighted adagrad with unified momentum","author":"zou","year":"2018","journal-title":"arXiv 1808 03408"},{"key":"ref19","first-page":"983","article-title":"On the convergence of stochastic gradient descent with adaptive stepsizes","author":"li","year":"2018","journal-title":"Proc AISTATS"},{"key":"ref4","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2016","journal-title":"arXiv 1609 04836"},{"key":"ref3","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016","journal-title":"arXiv 1608 03983"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2018.9010121"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/BF01584842"},{"key":"ref9","article-title":"Adaptive bound optimization for online convex optimization","author":"mcmahan","year":"2010","journal-title":"arXiv 1002 4908"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref42","first-page":"7313","article-title":"Global convergence of block coordinate descent in deep learning","author":"zeng","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01382-3"},{"key":"ref44","first-page":"1475","article-title":"Linear convergence of adaptive stochastic gradient descent","author":"xie","year":"2020","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref43","article-title":"Convergence analysis of a momentum algorithm with adaptive step size for non convex optimization","author":"barakat","year":"2019","journal-title":"J Control Optim"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09271900.pdf?arnumber=9271900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:15Z","timestamp":1652194215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9271900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3038535","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}