{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:36:11Z","timestamp":1775680571443,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFE0205500"],"award-info":[{"award-number":["2023YFE0205500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203374"],"award-info":[{"award-number":["62203374"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2024A1515010160"],"award-info":[{"award-number":["2024A1515010160"]}],"id":[{"id":"10.13039\/501100001321","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":[[2026,2]]},"DOI":"10.1109\/tnnls.2025.3610665","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T17:55:50Z","timestamp":1758822950000},"page":"673-685","source":"Crossref","is-referenced-by-count":2,"title":["<i>Ape<\/i>\n                    Optimizer: A p-Power Adaptive Filter-Based Approach for Deep Learning Optimization"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6671-931X","authenticated-orcid":false,"given":"Yufei","family":"Jin","sequence":"first","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"given":"Han","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"given":"Xinrui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"given":"Yingche","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8737-4210","authenticated-orcid":false,"given":"Zhuoran","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3389454"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3216811"},{"key":"ref5","first-page":"111","article-title":"Natural language processing","volume-title":"Deep Learning: From Big Data to Artificial Intelligence With R","author":"Tuffery","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3384987"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3400451"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3462790"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref14","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref15","article-title":"Perturbed iterate SGD for Lipschitz continuous loss functions with numerical error and adaptive step sizes","author":"Metel","year":"2022","journal-title":"arXiv:2211.04655"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1229\/1\/012046"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955777"},{"key":"ref18","article-title":"Incorporating Nesterov momentum into Adam","volume-title":"Proc. Int. Conf. Learn. Represent. Workshops","author":"Dozat","year":"2016"},{"key":"ref19","article-title":"On the convergence of Adam and beyond","author":"Reddi","year":"2019","journal-title":"arXiv:1904.09237"},{"key":"ref20","article-title":"On the heavy-tailed theory of stochastic gradient descent for deep neural networks","author":"\u015eim\u015fekli","year":"2019","journal-title":"arXiv:1912.00018"},{"key":"ref21","first-page":"8970","article-title":"Fractional underdamped Langevin dynamics: Retargeting SGD with momentum under heavy-tailed gradient noise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"\u015eim\u015fekli"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1090\/mmono\/065"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-1223-2_23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21236\/AD0241531"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479472"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"issue":"61","key":"ref27","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":"ref28","article-title":"Coursera: Neural networks for machine learning","author":"Tieleman","year":"2012"},{"key":"ref29","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"arXiv:1212.5701"},{"key":"ref30","article-title":"AdamP: Slowing down the slowdown for momentum optimizers on scale-invariant weights","author":"Heo","year":"2020","journal-title":"arXiv:2006.08217"},{"key":"ref31","first-page":"18795","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhuang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213677"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2963066"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3255783"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0967-0661(96)82838-3"},{"key":"ref36","volume-title":"Fundamentals of Adaptive Filtering","author":"Sayed","year":"2003"},{"key":"ref37","volume-title":"Signal Processing With Alpha-Stable Distributions and Applications","author":"Nikias","year":"1995"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.880306"},{"key":"ref39","article-title":"On the variance of the adaptive learning rate and beyond","author":"Liu","year":"2019","journal-title":"arXiv:1908.03265"},{"key":"ref40","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref41","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref42","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.05431"},{"key":"ref46","article-title":"Densely connected convolutional networks","author":"Huang","year":"2016","journal-title":"arXiv:1608.06993"},{"key":"ref47","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref49","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv:1511.06434"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-65"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11372199\/11180062.pdf?arnumber=11180062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:07:12Z","timestamp":1770671232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11180062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":50,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3610665","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}