{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:26:39Z","timestamp":1774052799842,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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 (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 Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tnnls.2022.3142726","type":"journal-article","created":{"date-parts":[[2022,1,29]],"date-time":"2022-01-29T00:56:12Z","timestamp":1643417772000},"page":"8108-8115","source":"Crossref","is-referenced-by-count":6,"title":["\u03f5-Approximation of Adaptive Leaning Rate Optimization Algorithms for Constrained Nonconvex Stochastic Optimization"],"prefix":"10.1109","volume":"34","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"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref12","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref14","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref11","first-page":"1","article-title":"Stochastic gradient descent in correlated settings: A study on Gaussian processes","volume":"33","author":"chen","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","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":"ref2","article-title":"Directional deep embedding and appearance learning for fast video object segmentation","author":"yin","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref1","article-title":"New generation deep learning for video object detection: A survey","author":"jiao","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"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":"ref16","first-page":"1","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3002590"},{"key":"ref18","first-page":"1","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","author":"zhuang","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"372","article-title":"A method for solving the convex programming problem with convergence rate ${O}(1\/k^2)$","volume":"27","author":"nesterov","year":"1983","journal-title":"Sov Math Doklady"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-9467-7","author":"bauschke","year":"2011","journal-title":"Convex Analysis and Monotone Operator Theory in Hilbert Spaces"},{"key":"ref25","first-page":"2408","article-title":"Optimizing neural networks with Kronecker-factored approximate curvature","volume":"37","author":"martens","year":"2015","journal-title":"Mach Learn Res"},{"key":"ref20","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":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref21","article-title":"Appropriate learning rates of adaptive learning rate optimization algorithms for training deep neural networks","author":"iiduka","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref28","author":"facchinei","year":"2003","journal-title":"Finite-Dimensional Variational Inequalities and Complementarity Problems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719451"},{"key":"ref29","author":"facchinei","year":"2003","journal-title":"Finite-Dimensional Variational Inequalities and Complementarity Problems"},{"key":"ref8","first-page":"1","article-title":"Measuring the effects of data parallelism on neural network training","volume":"20","author":"shallue","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref7","first-page":"1","article-title":"Which algorithmic choices matter at which batch sizes? Insights from a noisy quadratic model","author":"zhang","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2995800"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10273172\/09695982.pdf?arnumber=9695982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:18:56Z","timestamp":1698085136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9695982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":30,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3142726","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}