{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:16:21Z","timestamp":1730207781776,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/ciss48834.2020.1570627111","type":"proceedings-article","created":{"date-parts":[[2020,5,7]],"date-time":"2020-05-07T22:27:40Z","timestamp":1588890460000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Guaranteed Convergence of Training Convolutional Neural Networks via Accelerated Gradient Descent"],"prefix":"10.1109","author":[{"given":"Shuai","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sijia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pin-Yu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinjun","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","first-page":"4140","article-title":"Recovery guarantees for one-hidden-layer neural networks","author":"zhong","year":"0"},{"key":"ref30","article-title":"Learning non-overlapping convolutional neural networks with multiple kernels","author":"zhong","year":"2017","journal-title":"arXiv preprint arXiv 1711 03890"},{"key":"ref10","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":"ref11","first-page":"507","article-title":"Tensor factorization via matrix factorization","author":"kuleshov","year":"2015","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/72.554195"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref14","first-page":"597","article-title":"Convergence analysis of two-layer neural networks with ReLU activation","author":"li","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"4355","article-title":"Adding one neuron can eliminate all bad local minima","author":"liang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"855","article-title":"On the computational efficiency of training neural networks","author":"livni","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","volume":"87","author":"nesterov","year":"2013","journal-title":"Introductory Lectures on Convex Optimization A Basic Course"},{"key":"ref18","first-page":"5947","article-title":"Exploring generalization in deep learning","author":"neyshabur","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"Introduction to Optimization","year":"1987","author":"polyak","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2827299"},{"key":"ref4","article-title":"When is a convolutional filter easy to learn?","author":"du","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2016","journal-title":"arXiv preprint arXiv 1611 03530"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref6","article-title":"Guaranteed recovery of one-hidden-layer neural networks via cross entropy","author":"fu","year":"2018","journal-title":"arXiv preprint arXiv 1802 06463"},{"key":"ref29","first-page":"1524","article-title":"Learning one-hidden-layer relu networks via gradient descent","author":"zhang","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref5","first-page":"1338","article-title":"Gradient descent learns one-hidden-layer cnn: Don’t be afraid of spurious local minima","author":"du","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref8","first-page":"1225","article-title":"Train faster, generalize better: Stability of stochastic gradient descent","author":"hardt","year":"2016","journal-title":"International Conference on Machine Learning"},{"article-title":"Learning one-hidden-layer neural networks with landscape design","year":"0","author":"ge","key":"ref7"},{"key":"ref2","first-page":"605","article-title":"Globally optimal gradient descent for a convnet with gaussian inputs","author":"brutzkus","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref9","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref1","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"bousquet","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","article-title":"Learning representations by back-propagating errors","volume":"5","author":"rumelhart","year":"1988","journal-title":"Cognitive Modeling"},{"key":"ref22","first-page":"1135","article-title":"Distribution-specific hardness of learning neural networks","volume":"19","author":"shamir","year":"2018","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","first-page":"4430","article-title":"Spurious local minima are common in two- layer relu neural networks","author":"safran","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref24","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Int Conf Mach Learn"},{"key":"ref23","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":"ref26","article-title":"Analytical convergence regions of accelerated first-order methods in nonconvex optimization under regularity condition","author":"xiong","year":"2018","journal-title":"arXiv preprint arXiv 1810 06008"},{"key":"ref25","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":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"}],"event":{"name":"2020 54th Annual Conference on Information Sciences and Systems (CISS)","start":{"date-parts":[[2020,3,18]]},"location":"Princeton, NJ, USA","end":{"date-parts":[[2020,3,20]]}},"container-title":["2020 54th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9081570\/9086165\/09086272.pdf?arnumber=9086272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T11:47:05Z","timestamp":1656330425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9086272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ciss48834.2020.1570627111","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}