{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:45:23Z","timestamp":1773384323085,"version":"3.50.1"},"reference-count":35,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["CCF-1650913"],"award-info":[{"award-number":["CCF-1650913"]}]},{"name":"NSF","award":["DMS-1938106"],"award-info":[{"award-number":["DMS-1938106"]}]},{"name":"NSF","award":["DMS-1830210"],"award-info":[{"award-number":["DMS-1830210"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tsp.2020.3039360","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T01:21:08Z","timestamp":1606267268000},"page":"6696-6706","source":"Crossref","is-referenced-by-count":12,"title":["Approximation Algorithms for Training One-Node ReLU Neural Networks"],"prefix":"10.1109","volume":"68","author":[{"given":"Santanu S.","family":"Dey","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1410-3639","authenticated-orcid":false,"given":"Yao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2904921"},{"key":"ref32","first-page":"2908","article-title":"The multilinear structure of relu networks","author":"laurent","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2773497"},{"key":"ref30","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref35","article-title":"Agnostic learning of a single neuron with gradient descent","author":"frei","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"1452","article-title":"Approximation schemes for relu regression","author":"diakonikolas","year":"2020","journal-title":"Proc 33rd Int Conf Learn Theory"},{"key":"ref10","first-page":"605","article-title":"Globally optimal gradient descent for a convnet with gaussian inputs","author":"brutzkus","year":"0","journal-title":"Proc 34th Int Conf Mach Learn -Volume 70"},{"key":"ref11","article-title":"When is a convolutional filter easy to learn?","author":"du","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref12","first-page":"1339","article-title":"Gradient descent learns one-hidden-layer CNN: Don’t be afraid of spurious local minima","author":"du","year":"0","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref13","first-page":"1004","article-title":"Reliably learning the ReLU in polynomial time","author":"goel","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref14","first-page":"1783","article-title":"Learning one convolutional layer with overlapping patches","author":"goel","year":"0","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref16","first-page":"927","article-title":"Efficient learning of generalized linear and single index models with isotonic regression","author":"kakade","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","article-title":"The isotron algorithm: High-dimensional isotonic regression","author":"kalai","year":"2009","journal-title":"COLT"},{"key":"ref18","first-page":"855","article-title":"On the computational efficiency of training neural networks","author":"livni","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOS1637"},{"key":"ref28","article-title":"Test criteria for Pearson type III distributions","author":"mickey","year":"1963"},{"key":"ref4","article-title":"Understanding deep neural networks with rectified linear units","author":"arora","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref27","article-title":"Complexity of training ReLU neural network","author":"boob","year":"2018"},{"key":"ref3","first-page":"2472","article-title":"Sparse nonlinear regression: Parameter estimation under nonconvexity","volume":"48","author":"yang","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn (ICML)"},{"key":"ref6","article-title":"The computational complexity of training relu (s)","author":"manurangsi","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177697731"},{"key":"ref5","first-page":"2007","article-title":"Learning ReLUs via gradient descent","author":"soltanolkotabi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","first-page":"1004","article-title":"Reliably learning the relu in polynomial time","author":"goel","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref7","first-page":"2469","article-title":"Fitting relus via sgd and quantized SGD","author":"kalan","year":"0","journal-title":"Proc IEEE Int Symp Inf Theory (ISIT)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-008-9045-3"},{"key":"ref9","first-page":"5514","article-title":"On the complexity of learning neural networks","author":"song","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2011.12.030"},{"key":"ref20","first-page":"1674","article-title":"Non-convex learning via stochastic gradient langevin dynamics: A nonasymptotic analysis","author":"raginsky","year":"2017","journal-title":"Proc Conf Learn Theory"},{"key":"ref22","first-page":"10 612","article-title":"Tight sample complexity of learning one-hidden-layer convolutional neural networks","author":"cao","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"1524","article-title":"Learning one-hidden-layer relu networks via gradient descent","author":"zhang","year":"0","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOS1388"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/BF02985802","article-title":"The elements of statistical learning: Data mining, inference and prediction","volume":"27","author":"hastie","year":"2005","journal-title":"Math Intelligencer"},{"key":"ref26","article-title":"An approximation algorithm for training one-node relu neural network","author":"dey","year":"2018"},{"key":"ref25","article-title":"Extended comparisons of best subset selection, forward stepwise selection, and the LASSO","author":"hastie","year":"2017"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/78\/8933520\/9269442-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/8933520\/09269442.pdf?arnumber=9269442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:40:44Z","timestamp":1651070444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9269442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/tsp.2020.3039360","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}