{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:48:11Z","timestamp":1740181691753,"version":"3.37.3"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1563098"],"award-info":[{"award-number":["CCF-1563098"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Center for Science of Information, an NSF Science and Technology Center","award":["CCF-0939370"],"award-info":[{"award-number":["CCF-0939370"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/jsait.2020.2983192","type":"journal-article","created":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T19:55:56Z","timestamp":1585252556000},"page":"145-156","source":"Crossref","is-referenced-by-count":4,"title":["A Fourier-Based Approach to Generalization and Optimization in Deep Learning"],"prefix":"10.1109","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6049-9232","authenticated-orcid":false,"given":"Farzan","family":"Farnia","sequence":"first","affiliation":[]},{"given":"Jesse M.","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"David N.","family":"Tse","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Towards understanding the role of over-parametrization in generalization of neural networks","year":"2018","author":"neyshabur","key":"ref39"},{"article-title":"A PAC-Bayesian approach to spectrally-normalized margin bounds for neural networks","year":"2017","author":"neyshabur","key":"ref38"},{"article-title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","year":"2017","author":"harvey","key":"ref33"},{"journal-title":"Neural Network Learning Theoretical Foundations","year":"2009","author":"anthony","key":"ref32"},{"article-title":"Mad max: Affine spline insights into deep learning","year":"2018","author":"balestriero","key":"ref31"},{"key":"ref30","first-page":"374","article-title":"A spline theory of deep learning","volume":"80","author":"balestriero","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"article-title":"Stronger generalization bounds for deep nets via a compression approach","year":"2018","author":"arora","key":"ref37"},{"article-title":"Sharp minima can generalize for deep nets","year":"2017","author":"dinh","key":"ref36"},{"article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","year":"2016","author":"keskar","key":"ref35"},{"key":"ref34","first-page":"1376","article-title":"Norm-based capacity control in neural networks","author":"neyshabur","year":"2015","journal-title":"Proc Conf Learning Theory (COLT)"},{"key":"ref10","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"bartlett","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref40","first-page":"1908","article-title":"Learning polynomials with neural networks","author":"andoni","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref11","first-page":"793","article-title":"On the complexity of linear prediction: Risk bounds, margin bounds, and regularization","author":"kakade","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"The landscape of empirical risk for non-convex losses","year":"2016","author":"mei","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref14","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"bousquet","year":"2002","journal-title":"J Mach Learn Res"},{"journal-title":"The Nature of Statistical Learning Theory","year":"2013","author":"vapnik","key":"ref15"},{"article-title":"Train faster, generalize better: Stability of stochastic gradient descent","year":"2015","author":"hardt","key":"ref16"},{"key":"ref17","first-page":"415","article-title":"On the complexity of learning the kernel matrix","author":"bousquet","year":"2003","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"247","article-title":"Generalization bounds for learning kernels","author":"cortes","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML-10)"},{"article-title":"Reconciling modern machine learning practice and the bias-variance trade-off","year":"2018","author":"belkin","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref28","first-page":"907","article-title":"The power of depth for feedforward neural networks","author":"eldan","year":"2016","journal-title":"Proc 29th Annu Conf Learn Theory"},{"key":"ref3","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"article-title":"Exploring generalization in deep learning","year":"2017","author":"neyshabur","key":"ref6"},{"article-title":"Why deep neural networks for function approximation?","year":"2016","author":"liang","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref8"},{"key":"ref7","first-page":"2422","article-title":"Path-SGD: Path-normalized optimization in deep neural networks","author":"neyshabur","year":"2015","journal-title":"Proc 28th Int Conf Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"article-title":"Understanding deep learning requires rethinking generalization","year":"2016","author":"zhang","key":"ref1"},{"article-title":"Spectrally-normalized margin bounds for neural networks","year":"2017","author":"bartlett","key":"ref9"},{"article-title":"Surprises in high-dimensional ridgeless least squares interpolation","year":"2019","author":"hastie","key":"ref20"},{"article-title":"The generalization error of random features regression: Precise asymptotics and double descent curve","year":"2019","author":"mei","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849614"},{"key":"ref42","first-page":"2558","article-title":"A probabilistic framework for deep learning","author":"patel","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/18.256500"},{"key":"ref41","first-page":"3067","article-title":"Failures of gradient-based deep learning","author":"shalev-shwartz","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"article-title":"Benign overfitting in linear regression","year":"2019","author":"bartlett","key":"ref23"},{"key":"ref44","first-page":"1177","article-title":"Random features for large-scale kernel machines","volume":"3","author":"rahimi","year":"2007","journal-title":"Proc 20th Int Conf Neural Inf Process Syst (NIPS)"},{"article-title":"Distribution-specific hardness of learning neural networks","year":"2016","author":"shamir","key":"ref26"},{"journal-title":"Fourier Analysis on Groups","year":"2011","author":"rudin","key":"ref43"},{"article-title":"On the ability of neural nets to express distributions","year":"2017","author":"lee","key":"ref25"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/8768428\/9047867-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/8768428\/09047867.pdf?arnumber=9047867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:16:35Z","timestamp":1651065395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9047867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2020.2983192","relation":{},"ISSN":["2641-8770"],"issn-type":[{"type":"electronic","value":"2641-8770"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}