{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:30:17Z","timestamp":1774679417820,"version":"3.50.1"},"reference-count":28,"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":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61807021"],"award-info":[{"award-number":["61807021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Research and Development Funds","award":["JCYJ20170818094022586"],"award-info":[{"award-number":["JCYJ20170818094022586"]}]},{"name":"Shenzhen Science and Technology Program","award":["KQTD20170810150821146"],"award-info":[{"award-number":["KQTD20170810150821146"]}]},{"name":"Innovation and Entrepreneurship Project for Overseas High-Level Talents of Shenzhen","award":["KQJSCX20180327144037831"],"award-info":[{"award-number":["KQJSCX20180327144037831"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2998825","type":"journal-article","created":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T21:32:05Z","timestamp":1591047125000},"page":"102616-102628","source":"Crossref","is-referenced-by-count":1,"title":["On the Optimal Tradeoff Between Computational Efficiency and Generalizability of Oja\u2019s Algorithm"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4178-0934","authenticated-orcid":false,"given":"Xiangxiang","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shao-Lun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2017.51"},{"key":"ref11","first-page":"3410","article-title":"Nonlinear principal component analysis of noisy data","author":"hsieh","year":"2018","journal-title":"Proc IEEE Proc Int Conf Neural Netw"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1182-z"},{"key":"ref13","first-page":"645","article-title":"Diffusion approximations for online principal component estimation and global convergence","author":"li","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_2"},{"key":"ref15","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":"ref16","first-page":"205","article-title":"Averaged least-mean-squares: Bias-variance trade-offs and optimal sampling distributions","volume":"38","author":"defossez","year":"2015","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref17","first-page":"1","article-title":"Parallelizing stochastic gradient descent for least squares regression: Mini-batching, averaging, and model misspecification","volume":"18","author":"jain","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref18","article-title":"Don’t decay the learning rate, increase the batch size","author":"smith","year":"2017","journal-title":"arXiv 1711 00489"},{"key":"ref19","article-title":"Revisiting small batch training for deep neural networks","author":"masters","year":"2018","journal-title":"arXiv 1804 07612"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/S0266466600011129"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447113"},{"key":"ref27","author":"lecun","year":"1998","journal-title":"MNIST Handwritten Digit Database"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"ref6","volume":"3","author":"golub","year":"2012","journal-title":"Matrix Computations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849505"},{"key":"ref8","first-page":"257","article-title":"Convergence of stochastic gradient descent for PCA","author":"shamir","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00275687"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref9","first-page":"1147","article-title":"Streaming PCA: Matching matrix bernstein and near-optimal finite sample guarantees for Oja’s algorithm","author":"jain","year":"2016","journal-title":"Proc Conf Learn Theory"},{"key":"ref1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref20","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv 1706 02677"},{"key":"ref22","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1151"},{"key":"ref23","article-title":"The step decay schedule: A near optimal, geometrically decaying learning rate procedure for least squares","author":"ge","year":"2019","journal-title":"arXiv 1904 12838"},{"key":"ref26","first-page":"1731","article-title":"Train longer, generalize better: Closing the generalization gap in large batch training of neural networks","author":"hoffer","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(03)00138-2"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09104701.pdf?arnumber=9104701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:52:23Z","timestamp":1639770743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9104701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2998825","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}