{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T18:33:50Z","timestamp":1768588430361,"version":"3.49.0"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-1612985\/1806063"],"award-info":[{"award-number":["DMS-1612985\/1806063"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1934904"],"award-info":[{"award-number":["CCF-1934904"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1815101"],"award-info":[{"award-number":["CCF-1815101"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CAREER CCF-2005804"],"award-info":[{"award-number":["CAREER CCF-2005804"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Faculty Fellowship from the Black and Veatch Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/tit.2021.3065212","type":"journal-article","created":{"date-parts":[[2021,3,10]],"date-time":"2021-03-10T21:50:50Z","timestamp":1615413050000},"page":"4669-4692","source":"Crossref","is-referenced-by-count":12,"title":["Benefits of Jointly Training Autoencoders: An Improved Neural Tangent Kernel Analysis"],"prefix":"10.1109","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1576-5420","authenticated-orcid":false,"given":"Thanh V.","family":"Nguyen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9342-3755","authenticated-orcid":false,"given":"Raymond K. W.","family":"Wong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4574-8066","authenticated-orcid":false,"given":"Chinmay","family":"Hegde","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"203","article-title":"A probabilistic analysis of EM for mixtures of separated, spherical Gaussians","volume":"8","author":"dasgupta","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref11","first-page":"1","article-title":"Identity crisis: Memorization and generalization under extreme overparameterization","author":"zhang","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref12","article-title":"Memorization in overparameterized autoencoders","author":"radhakrishnan","year":"2019"},{"key":"ref13","first-page":"1211","article-title":"Empirical study of the benefits of overparameterization in learning latent variable models","author":"buhai","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437533"},{"key":"ref15","first-page":"2858","article-title":"On the dynamics of gradient descent for autoencoders","author":"nguyen","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"113","article-title":"Simple, efficient, and neural algorithms for sparse coding","author":"arora","year":"2015","journal-title":"Proc Conf Learn Theory"},{"key":"ref17","first-page":"3852","article-title":"A provable approach for double-sparse coding","author":"nguyen","year":"2018","journal-title":"Proc Am Assoc Art Intell"},{"key":"ref18","first-page":"1","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","author":"lee","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"1","article-title":"On exact computation with an infinitely wide neural net","author":"arora","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","first-page":"1","article-title":"Gradient descent provably optimizes overparameterized neural networks","author":"du","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","article-title":"Stochastic gradient descent optimizes over-parameterized deep ReLU networks","author":"zou","year":"2018","journal-title":"arXiv 1811 08888"},{"key":"ref6","first-page":"322","article-title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","author":"arora","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991332"},{"key":"ref8","first-page":"8571","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","author":"jacot","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"1","article-title":"An improved analysis of training over-parameterized deep neural networks","author":"zou","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","author":"allen-zhu","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"ref1","first-page":"8157","article-title":"Learning overparameterized neural networks via stochastic gradient descent on structured data","author":"li","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"1216","article-title":"Diverse neural network learns true target functions","author":"xie","year":"2017","journal-title":"Proc Artif Intell Statist"},{"key":"ref22","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","author":"du","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","first-page":"4995","article-title":"Invariance of weight distributions in rectified MLPs","author":"tsuchida","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","article-title":"Quadratic suffices for over-parametrization via matrix chernoff bound","author":"song","year":"2019","journal-title":"arXiv 1906 03593"},{"key":"ref23","first-page":"1","article-title":"On random deep weight-tied autoencoders: Exact asymptotic analysis, phase transition, and implications to training","author":"li","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref26","first-page":"4140","article-title":"Recovery guarantees for one-hidden-layer neural networks","author":"zhong","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9099-z"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/9457114\/9374468-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/9457114\/09374468.pdf?arnumber=9374468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:27Z","timestamp":1652194467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9374468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":26,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tit.2021.3065212","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}