{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:40:10Z","timestamp":1778632810445,"version":"3.51.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572152 (to HZ)"],"award-info":[{"award-number":["61572152 (to HZ)"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Science Technology and Innovation Commission of Shenzhen Municipality","doi-asserted-by":"publisher","award":["JSGG20160229125049615"],"award-info":[{"award-number":["JSGG20160229125049615"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Science Technology and Innovation Commission of Shenzhen Municipality","doi-asserted-by":"publisher","award":["JCYJ20151029173639477 (to HZ)"],"award-info":[{"award-number":["JCYJ20151029173639477 (to HZ)"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3002884","type":"journal-article","created":{"date-parts":[[2020,6,16]],"date-time":"2020-06-16T21:07:06Z","timestamp":1592341626000},"page":"112805-112813","source":"Crossref","is-referenced-by-count":15,"title":["PACL: Piecewise Arc Cotangent Decay Learning Rate for Deep Neural Network Training"],"prefix":"10.1109","volume":"8","author":[{"given":"Haixu","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0733-4746","authenticated-orcid":false,"given":"Jihong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henggui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Gradient descent converges to minimizers","author":"lee","year":"2016","journal-title":"arXiv 1602 04915"},{"key":"ref38","first-page":"265","article-title":"On optimization methods for deep learning","author":"le","year":"2011","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","author":"le","year":"2015","journal-title":"Tiny imagenet visual recognition challenge"},{"key":"ref30","first-page":"14","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"krizhevsky","year":"2009","journal-title":"Handbook of Systemic Autoimmune Diseases"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref36","article-title":"Squeeze-and-excitation networks","author":"jie","year":"0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref34","article-title":"Wide residual networks","author":"zagoruyko","year":"0"},{"key":"ref10","article-title":"Constant step size stochastic gradient descent for probabilistic modeling","author":"babichev","year":"0"},{"key":"ref11","first-page":"1","article-title":"Deep learning","author":"jeff","year":"2017","journal-title":"Genetic Program Evolvable Mach"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1007\/978-3-642-35289-8_26","article-title":"Practical recommendations for gradient-based training of deep architectures","author":"bengio","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT.2017.8359963"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00052"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.12677\/HJDM.2018.84020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref17","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305126"},{"key":"ref19","article-title":"Large-scale machine learning with stochastic gradient descent","author":"bottou","year":"0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960523"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref27","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/72.377972"},{"key":"ref6","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref29","first-page":"1504","article-title":"Equilibrated adaptive learning rates for non-convex optimization","author":"dauphin","year":"2015","journal-title":"Proc 29th Annu Conf Neural Inf Process Syst"},{"key":"ref5","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":"ref8","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0"},{"key":"ref7","first-page":"26","article-title":"Lecture 6.5-RmsProp: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref2","first-page":"1","article-title":"Review on the application of deep convolution neural network in computer vision","volume":"31","author":"lu","year":"2016","journal-title":"J Data Acquisition Process"},{"key":"ref9","article-title":"Research progress of random gradient descent","author":"shi","year":"2019","journal-title":"ACTA Automatica Sinica"},{"key":"ref1","article-title":"Sequential click prediction for sponsored search with recurrent neural networks","author":"zhang","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref22","first-page":"536","article-title":"Méthode générale pour la résolution des systemes d’équations simultanées","volume":"25","author":"cauchy","year":"1847","journal-title":"Comp Rend Sci Paris"},{"key":"ref21","first-page":"187","author":"bertsekas","year":"1999","journal-title":"Nonlinear Programming"},{"key":"ref24","first-page":"15","article-title":"Online algorithms and stochastic approximations","author":"bottou","year":"1998","journal-title":"Online Learning and Neural Networks"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/PGEC.1967.264666"},{"key":"ref26","first-page":"262","article-title":"Classification of radar returns from the ionosphere using neural networks","volume":"10","author":"sigillito","year":"1989","journal-title":"Johns Hopkins APL Tech Dig"},{"key":"ref25","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume":"28","author":"sutskever","year":"2013","journal-title":"Proc ICML"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09118940.pdf?arnumber=9118940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:52:44Z","timestamp":1639770764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9118940\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3002884","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}