{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:21:28Z","timestamp":1740169288141,"version":"3.37.3"},"reference-count":20,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["21K11773"],"award-info":[{"award-number":["21K11773"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3120749","type":"journal-article","created":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T23:44:30Z","timestamp":1634341470000},"page":"143807-143823","source":"Crossref","is-referenced-by-count":3,"title":["Unified Algorithm Framework for Nonconvex Stochastic Optimization in Deep Neural Networks"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2607-4369","authenticated-orcid":false,"given":"Yini","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9173-6723","authenticated-orcid":false,"given":"Hideaki","family":"Iiduka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"zhuang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3107415"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2695498"},{"key":"ref13","first-page":"1","article-title":"On the convergence of a class of Adam-type algorithms for non-convex optimization","author":"chen","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3049845"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921369"},{"key":"ref16","first-page":"1","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"article-title":"An analysis of particle swarm optimizers","year":"2001","author":"van den bergh","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2008.919004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.08.030"},{"key":"ref4","first-page":"1","article-title":"Robustness analysis of non-convex stochastic gradient descent using biased expectations","volume":"33","author":"scaman","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2919987"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref6"},{"key":"ref5","first-page":"1","article-title":"Stochastic Polyak step-size for SGD: An adaptive learning rate for fast convergence","volume":"130","author":"loizou","year":"2021","journal-title":"Proc 24th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref8","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3002590"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3045071"},{"key":"ref9","first-page":"1","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5267\/j.ijiec.2012.03.007"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09576705.pdf?arnumber=9576705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T22:26:23Z","timestamp":1645482383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9576705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3120749","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}