{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:52:54Z","timestamp":1774630374001,"version":"3.50.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP18K11184"],"award-info":[{"award-number":["JP18K11184"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","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 Trans. Cybern."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tcyb.2021.3107415","type":"journal-article","created":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T20:09:37Z","timestamp":1631131777000},"page":"13250-13261","source":"Crossref","is-referenced-by-count":77,"title":["Appropriate Learning Rates of Adaptive Learning Rate Optimization Algorithms for Training Deep Neural Networks"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9173-6723","authenticated-orcid":false,"given":"Hideaki","family":"Iiduka","sequence":"first","affiliation":[{"name":"Department of Computer Science, Meiji University, Kanagawa, Japan"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4"},{"key":"ref11","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":"ref12","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref13","first-page":"1","article-title":"On the convergence of adam and beyond","author":"reddi","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"37","author":"xu","year":"2015","journal-title":"Mach Learn Res"},{"key":"ref15","author":"arjovsky","year":"2017","journal-title":"Wasserstein GAN"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","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":"ref18","first-page":"1","article-title":"Convergence rates for the stochastic gradient descent method for non-convex objective functions","volume":"21","author":"fehrman","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref19","first-page":"1","article-title":"Robustness analysis of non-convex stochastic gradient descent using biased expectations","volume":"33","author":"scaman","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref27","first-page":"1","article-title":"SPIDER: Near-optimal non-convex optimization via stochastic path-integrated differential estimator","volume":"31","author":"fang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Predicting network controllability robustness: A convolutional neural network approach","author":"lou","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810817"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623499362111"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/110848864"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2367591"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2283296"},{"key":"ref9","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref20","first-page":"1","article-title":"Stochastic gradient descent in correlated settings: A study on Gaussian processes","volume":"33","author":"chen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"1","article-title":"Parallelized stochastic gradient descent","volume":"23","author":"zinkevich","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref21","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 Stat (AISTATS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3002590"},{"key":"ref23","author":"facchinei","year":"2003","journal-title":"Finite-Dimensional Variational Inequalities and Complementarity Problems"},{"key":"ref26","first-page":"1","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"zhuang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"1","article-title":"Stochastic optimization for performative prediction","volume":"33","author":"mendler-d\u00fcnner","year":"2020","journal-title":"Advances in neural information processing systems"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9954939\/09531335.pdf?arnumber=9531335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:12:47Z","timestamp":1670872367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9531335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":29,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2021.3107415","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}