{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:41:50Z","timestamp":1781797310995,"version":"3.54.5"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025208"],"award-info":[{"award-number":["62025208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010878","name":"State Administration for Science, Technology and Industry for National Defense","doi-asserted-by":"publisher","award":["WDZC20235250118"],"award-info":[{"award-number":["WDZC20235250118"]}],"id":[{"id":"10.13039\/501100010878","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tpami.2024.3387399","type":"journal-article","created":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T18:58:05Z","timestamp":1712861885000},"page":"6731-6747","source":"Crossref","is-referenced-by-count":14,"title":["XGrad: Boosting Gradient-Based Optimizers With Weight Prediction"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9041-3244","authenticated-orcid":false,"given":"Lei","family":"Guan","sequence":"first","affiliation":[{"name":"Department of Mathematics, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9743-2034","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6845-4754","authenticated-orcid":false,"given":"Yanqi","family":"Shi","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6301-6331","authenticated-orcid":false,"given":"Jian","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Mathematics, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref2","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref3","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref4","first-page":"1","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2018","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref5","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1063\/5.0083060"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemmater.9b01294"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-021-00650-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"issue":"8","key":"ref17","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref18","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref20","article-title":"XPipe: Efficient pipeline model parallelism for multi-gpu dnn training","author":"Guan","year":"2019"},{"key":"ref21","article-title":"Efficient and robust parallel DNN training through model parallelism on multi-GPU platform","author":"Chen","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-33374-3_26"},{"key":"ref23","article-title":"Coursera Neural Networks for Machine Learning lecture 6","author":"Hinton","year":"2018"},{"key":"ref24","first-page":"18 795","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"Zhuang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00179"},{"issue":"7","key":"ref26","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":"ref27","first-page":"1","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"Luo","year":"2019","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref28","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","author":"Liu","year":"2020","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref29","article-title":"Symbolic discovery of optimization algorithms","volume":"36","author":"Chen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref30","first-page":"747","article-title":"The extragradient method for finding saddle points and other problems","volume":"12","author":"Korpelevich","year":"1976","journal-title":"Matecon"},{"key":"ref31","first-page":"16 223","article-title":"Explore aggressively, update conservatively: Stochastic extragradient methods with variable stepsize scaling","volume":"33","author":"Hsieh","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref35","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref36","first-page":"1","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref37","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref38","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w16-2323"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref44","article-title":"Adadelta: An adaptive learning rate method","author":"Zeiler","year":"2012"},{"key":"ref45","first-page":"1","article-title":"On the convergence of adam and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddi"},{"issue":"3","key":"ref46","first-page":"543","article-title":"A method of solving a convex programming problem with convergence rate $o(1\/k^{2})$o(1\/k2)","volume":"269","author":"Nesterov","year":"1983","journal-title":"Doklady Akademii Nauk"},{"key":"ref47","first-page":"1","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dozat","year":"2016"},{"key":"ref48","first-page":"9815","article-title":"Adaptive methods for nonconvex optimization","volume":"31","author":"Zaheer","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref49","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. Representations"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10666888\/10496892.pdf?arnumber=10496892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:47:29Z","timestamp":1725684449000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10496892\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":48,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3387399","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}