{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T22:49:44Z","timestamp":1773960584258,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"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":["61772374"],"award-info":[{"award-number":["61772374"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876133"],"award-info":[{"award-number":["61876133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11771012"],"award-info":[{"award-number":["11771012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61977038"],"award-info":[{"award-number":["61977038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61603162"],"award-info":[{"award-number":["61603162"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876074"],"award-info":[{"award-number":["61876074"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["LY17F030004"],"award-info":[{"award-number":["LY17F030004"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Two Thousand Talents Plan of Jiangxi Province"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tnnls.2020.2979228","type":"journal-article","created":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T20:57:31Z","timestamp":1585861051000},"page":"748-762","source":"Crossref","is-referenced-by-count":27,"title":["Random Sketching for Neural Networks With ReLU"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0435-0609","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1719-3358","authenticated-orcid":false,"given":"Jinshan","family":"Zeng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5122-9153","authenticated-orcid":false,"given":"Shao-Bo","family":"Lin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.06.016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jco.2018.09.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/060678555"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-013-9183-5"},{"key":"ref30","article-title":"A representer theorem for deep neural networks","author":"unser","year":"2018","journal-title":"arXiv 1802 09210"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1007\/b97848","author":"gy\u00f6rfy","year":"2002","journal-title":"A Distribution-Free Theory of Nonparametric Regression"},{"key":"ref36","author":"steinwart","year":"2008","journal-title":"Support Vector Machines"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10444-004-7206-2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-00-01240-0"},{"key":"ref28","first-page":"1177","article-title":"Random features for large-scale kernel machines","author":"rahimi","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141097322959"},{"key":"ref29","article-title":"Lecture notes on randomized linear algebra","author":"mahoney","year":"2016","journal-title":"arXiv 1608 04481"},{"key":"ref2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref20","first-page":"1","article-title":"Spurious local minima are common in two-layer ReLU neural networks","author":"safran","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511618796"},{"key":"ref21","first-page":"8157","article-title":"Learning overparameterized neural networks via stochastic gradient descent on structured data","author":"li","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","first-page":"682","article-title":"Using the Nyström method to speed up kernel machines","volume":"13","author":"williams","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-35289-8","volume":"7700","author":"montavon","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref26","article-title":"Learning through deterministic assignment of hidden parameters","author":"fang","year":"2018","journal-title":"IEEE Trans Cybern"},{"key":"ref25","first-page":"1","article-title":"Revisiting the Nyström method for improved large-scale machine learning","volume":"17","author":"gittens","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2771463"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2011.01.001"},{"key":"ref56","author":"demuth","year":"2010","journal-title":"Neural network toolbox TM 6 MathWorks"},{"key":"ref55","author":"adams","year":"1975","journal-title":"Sobolev Spaces"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141003432316"},{"key":"ref53","volume":"161","author":"borwein","year":"2012","journal-title":"Polynomials and Polynomial Inequalities"},{"key":"ref52","author":"wang","year":"2000","journal-title":"Harmonic Analysis and Approximation on the Unit Sphere"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2018.00014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2016.04.003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1142\/S0219530519400074"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2951788"},{"key":"ref15","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-018-09409-5"},{"key":"ref17","first-page":"265","article-title":"On optimization methods for deep learning","author":"le","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref18","article-title":"A convergence analysis of nonlinearly constrained ADMM in deep learning","author":"zeng","year":"2019","journal-title":"arXiv 1902 02060"},{"key":"ref19","first-page":"1","article-title":"Global convergence of block coordinate descent in deep learning","author":"zeng","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref3","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1142\/S0219530518500203"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1994-1240656-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1142\/S0219530516400042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018993908478"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2868980"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2634401"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.08.019"},{"key":"ref45","first-page":"1","article-title":"A convergence theory for deep learning via over-parameterization","author":"allen-zhu","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref48","volume":"7","author":"pinkus","year":"2012","journal-title":"n-Widths in Approximation Theory"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-017-9379-1"},{"key":"ref42","first-page":"597","article-title":"Convergence analysis of two-layer neural networks with ReLU activation","author":"li","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref41","first-page":"3404","article-title":"An analytical formula of population gradient for two-layered ReLU network and its applications in convergence and critical point analysis","author":"tian","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref44","first-page":"1","article-title":"Gradient descent provably optimizes over-parameterized neural networks","author":"du","year":"2019","journal-title":"Proc 7th Int Conf Learn Represent"},{"key":"ref43","first-page":"1339","article-title":"Gradient descent learns one-hiddenlayer CNN: Don’t be afraid of spurious local minima","author":"du","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9346113\/09055387.pdf?arnumber=9055387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:11Z","timestamp":1652194391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9055387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":56,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2979228","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}