{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T23:20:02Z","timestamp":1772839202036,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Hundred Talents Program of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Y9BEJ11001"],"award-info":[{"award-number":["Y9BEJ11001"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Workstation of Suzhou Institute of Nano-Tech and Nano-Bionics","award":["E010210101"],"award-info":[{"award-number":["E010210101"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876155"],"award-info":[{"award-number":["61876155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Science and Technology Program","award":["BE2020006-4"],"award-info":[{"award-number":["BE2020006-4"]}]},{"DOI":"10.13039\/501100000266","name":"U.K. Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/M026981\/1"],"award-info":[{"award-number":["EP\/M026981\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"U.K. Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T021063\/1"],"award-info":[{"award-number":["EP\/T021063\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"U.K. Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T024917\/1"],"award-info":[{"award-number":["EP\/T024917\/1"]}],"id":[{"id":"10.13039\/501100000266","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":[[2023,9]]},"DOI":"10.1109\/tnnls.2022.3143554","type":"journal-article","created":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T20:21:42Z","timestamp":1646943702000},"page":"6515-6529","source":"Crossref","is-referenced-by-count":10,"title":["FastAdaBelief: Improving Convergence Rate for Belief-Based Adaptive Optimizers by Exploiting Strong Convexity"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5311-1482","authenticated-orcid":false,"given":"Yangfan","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Nano-Tech and Nano-Bionics, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3034-9639","authenticated-orcid":false,"given":"Kaizhu","family":"Huang","sequence":"additional","affiliation":[{"name":"Data Science Research Center, Duke Kunshan University, Kunshan, China"}]},{"given":"Cheng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Suzhou Institute of Nano-Tech and Nano-Bionics (SINANO), Chinese Academy of Sciences, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6082-4541","authenticated-orcid":false,"given":"Xuguang","family":"Wang","sequence":"additional","affiliation":[{"name":"Suzhou Institute of Nano-Tech and Nano-Bionics (SINANO), Chinese Academy of Sciences, Suzhou, China"}]},{"given":"Amir","family":"Hussain","sequence":"additional","affiliation":[{"name":"School of Computing, Edinburgh Napier University, Edinburgh, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4083-4731","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Nano-Tech and Nano-Bionics, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref13","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2875452"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2893289"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2931393"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","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":"Sov Math Doklady"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2884191"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2952219"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040782"},{"key":"ref10","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","author":"zinkevich","year":"2003","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2947563"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2017.2748388"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.03.011"},{"key":"ref17","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref16","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","first-page":"9793","article-title":"Adaptive methods for nonconvex optimization","author":"zaheer","year":"2018","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref23","article-title":"SAdam: A variant of Adam for strongly convex functions","author":"wang","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref26","article-title":"Adaptive bound optimization for online convex optimization","author":"mcmahan","year":"2010","journal-title":"arXiv 1002 4908"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref20","first-page":"404","article-title":"Dissecting Adam: The sign, magnitude and variance of stochastic gradients","volume":"80","author":"balles","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","first-page":"18795","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"zhuang","year":"2020","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref21","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2916868"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2908958"},{"key":"ref29","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","volume":"48","author":"liu","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn"},{"key":"ref8","first-page":"2545","article-title":"Variants of RMSProp and adagrad with logarithmic regret bounds","volume":"70","author":"mukkamala","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","first-page":"2611","article-title":"Fast and scalable Bayesian deep learning by weight-perturbation in Adam","volume":"80","author":"khan","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04718-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2868835"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3014896"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2967415"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2943337"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10237282\/09732534.pdf?arnumber=9732534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:25:54Z","timestamp":1695666354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9732534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":36,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3143554","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}