{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T23:58:22Z","timestamp":1786060702258,"version":"3.56.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Ministry of Higher Education Malaysia, Fundamental Research Grant Scheme","award":["FRGS\/1\/2022\/STG06\/USM\/02\/4"],"award-info":[{"award-number":["FRGS\/1\/2022\/STG06\/USM\/02\/4"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3340719","type":"journal-article","created":{"date-parts":[[2023,12,7]],"date-time":"2023-12-07T19:40:53Z","timestamp":1701978053000},"page":"139171-139186","source":"Crossref","is-referenced-by-count":66,"title":["ps-CALR: Periodic-Shift Cosine Annealing Learning Rate for Deep Neural Networks"],"prefix":"10.1109","volume":"11","author":[{"given":"Olanrewaju Victor","family":"Johnson","sequence":"first","affiliation":[{"name":"School of Computer Sciences, Universiti Sains Malaysia, Gelugor, Penang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5539-1959","authenticated-orcid":false,"given":"Chew","family":"Xinying","sequence":"additional","affiliation":[{"name":"School of Computer Sciences, Universiti Sains Malaysia, Gelugor, Penang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2646-6477","authenticated-orcid":false,"given":"Khai Wah","family":"Khaw","sequence":"additional","affiliation":[{"name":"School of Management, Universiti Sains Malaysia, Gelugor, Penang, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2096-5865","authenticated-orcid":false,"given":"Ming Ha","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Engineering, Swinburne University of Technology, Sarawak Campus, Kuching, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ism46123.2019.00049"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10534-6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/1475921718757405"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2018.04.066"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10015-023-00852-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2992063"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10049-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.gpb.2017.07.003"},{"key":"ref10","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.03.050"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/access.2018.2874767"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.12.009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.12.039"},{"key":"ref16","first-page":"1","article-title":"Control batch size and learning rate to generalize well: Theoretical and empirical evidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"He"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cec45853.2021.9504761"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8111267"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/aike.2019.00060"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3570508"},{"key":"ref22","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016","journal-title":"arXiv:1609.04747"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23741-6_6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2021.0120885"},{"key":"ref25","article-title":"Generalized Polyak step size for first order optimization with momentum","author":"Wang","year":"2023","journal-title":"arXiv:2305.12939"},{"key":"ref26","first-page":"1306","article-title":"Stochastic Polyak step-size for SGD: An adaptive learning rate for fast convergence","volume-title":"Proc. Mach. Learn. Res.","volume":"130","author":"Loizou"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-021-01628-3"},{"key":"ref28","first-page":"1","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Keskar"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1908636117"},{"key":"ref30","article-title":"When do flat minima optimizers work?","author":"Kaddour","year":"2022","journal-title":"arXiv:2202.00661"},{"key":"ref31","first-page":"1","article-title":"A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1103\/physrevlett.127.278301"},{"key":"ref33","first-page":"1019","article-title":"Sharp minima can generalize for deep nets","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Dinh"},{"key":"ref34","first-page":"1","article-title":"Super convergence cosine annealing with warm-up learning rate","volume-title":"Proc. 2nd Int. Conf. Artif. Intell., Big Data Algorithms (CAIBDA)","author":"Liu"},{"key":"ref35","first-page":"1","article-title":"Towards explaining the regularization effect of initial large learning rate in training neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03413-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.32604\/iasc.2023.030628"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icapai55158.2022.9801574"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3579654.3579666"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2023.031481"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tencon.2019.8929465"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/int.22883"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/sym12040660"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115357"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10162029"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3107415"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/scisisis50064.2020.9322765"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86523-8_23"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.014"},{"key":"ref50","first-page":"24430","article-title":"Adaptive inertia: Disentangling the effects of adaptive learning rate and momentum","volume-title":"Proc. Mach. Learn. Res.","volume":"162","author":"Xie"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3041525"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/swc50871.2021.00036"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-11140-w"},{"key":"ref54","first-page":"1","article-title":"Snapshot ensembles: Train 1, get M for free","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Huang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/i2mtc48687.2022.9806568"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1031"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/icetci55171.2022.9921361"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.06.007"},{"key":"ref59","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref60","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10348553.pdf?arnumber=10348553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:19:55Z","timestamp":1705022395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10348553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3340719","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}