{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:01:44Z","timestamp":1740132104107,"version":"3.37.3"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["ERC-StG 757497"],"award-info":[{"award-number":["ERC-StG 757497"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tpami.2022.3155238","type":"journal-article","created":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T20:40:04Z","timestamp":1646167204000},"page":"27-37","source":"Crossref","is-referenced-by-count":1,"title":["A Function Space Analysis of Finite Neural Networks With Insights From Sampling Theory"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2830-0297","authenticated-orcid":false,"given":"Raja","family":"Giryes","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Tel Aviv University, Tel Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2924","article-title":"On the number of linear regions of deep neural networks","author":"montufar","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS1990"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.917416"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/78.650255"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1977.10771"},{"key":"ref30","article-title":"Generalization bounds of stochastic gradient descent for wide and deep neural networks","author":"cao","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1700203114"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00041-010-9156-z"},{"journal-title":"Real and Complex Analysis","year":"1987","author":"rudin","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2003.09.017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1806579115"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/78.995071"},{"key":"ref11","first-page":"8572","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","author":"lee","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref12","first-page":"8141","article-title":"On exact computation with an infinitely wide neural net","author":"arora","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1006\/acha.1998.0248"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2015.12.005"},{"key":"ref15","first-page":"5301","article-title":"On the spectral bias of neural networks","author":"rahaman","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36708-4_22"},{"key":"ref17","article-title":"A spectral perspective of DNN robustness to label noise","author":"bar","year":"2022","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907369117"},{"key":"ref19","article-title":"Why are convolutional nets more sample-efficient than fully-connected nets?","author":"li","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","first-page":"9709","article-title":"Regularization matters: Generalization and optimization of neural nets v.s. their induced kernel","author":"wei","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"article-title":"On tighter generalization bound for deep neural networks: CNNs, ResNets, and beyond","year":"2018","author":"li","key":"ref27"},{"key":"ref3","article-title":"A function space view of bounded norm infinite width ReLU nets: The multivariate case","author":"ongie","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref6","first-page":"6231","article-title":"The expressive power of neural networks: A view from the width","author":"lu","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5736"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref8","first-page":"8571","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","author":"jacot","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref7","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","first-page":"8376","article-title":"Gradient dynamics of shallow univariate ReLU networks","author":"williams","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref9","first-page":"2937","article-title":"On lazy training in differentiable programming","author":"chizat","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref1","first-page":"2667","article-title":"How do infinite width bounded norm networks look in function space?","author":"savarese","year":"2019","journal-title":"Proc 32nd Annu Conf Learn Theory"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144501386986"},{"key":"ref20","first-page":"374","article-title":"A spline theory of deep learning","author":"balestriero","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/5.843002"},{"journal-title":"Sampling Theory Beyond Bandlimited Systems","year":"2015","author":"eldar","key":"ref48"},{"key":"ref22","first-page":"1376","article-title":"Norm-based capacity control in neural networks","author":"neyshabur","year":"2015","journal-title":"Proc 28th Conf Learn Theory"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s00041-003-0004-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993164"},{"key":"ref42","article-title":"Gradient descent maximizes the margin of homogeneous neural networks","author":"lyu","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","first-page":"5960","article-title":"Understanding generalization and optimization performance of deep CNNs","author":"zhou","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref41","first-page":"153","author":"jakubovitz","year":"2019","journal-title":"Generalization error in deep learning"},{"key":"ref23","first-page":"297","article-title":"Size-independent sample complexity of neural networks","author":"golowich","year":"2018","journal-title":"Proc 31st Conf Learn Theory"},{"key":"ref44","first-page":"1","article-title":"Breaking the curse of dimensionality with convex neural networks","volume":"18","author":"bach","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref26","first-page":"6240","article-title":"Spectrally-normalized margin bounds for neural networks","author":"bartlett","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref43","first-page":"4683","article-title":"Lexicographic and depth-sensitive margins in homogeneous and non-homogeneous deep models","author":"nacson","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2708039"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9970415\/09723557.pdf?arnumber=9723557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:12:24Z","timestamp":1672081944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9723557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":48,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3155238","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2023,1,1]]}}}