{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:08:55Z","timestamp":1740100135698,"version":"3.37.3"},"reference-count":44,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,25]]},"DOI":"10.23919\/acc50511.2021.9483256","type":"proceedings-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T20:29:16Z","timestamp":1627504156000},"page":"2587-2594","source":"Crossref","is-referenced-by-count":0,"title":["No Spurious Solutions in Non-convex Matrix Sensing: Structure Compensates for Isometry"],"prefix":"10.23919","author":[{"given":"Igor","family":"Molybog","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Somayeh","family":"Sojoudi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javad","family":"Lavaei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A tutorial on bayesian optimization","author":"frazier","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2017.2691473"},{"key":"ref33","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Escaping saddles with stochastic gradients","author":"daneshmand","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1108\/OIR-11-2016-0339"},{"key":"ref30","article-title":"Non-square matrix sensing without spurious local minima via the burer-monteiro approach","author":"park","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/17M1150116"},{"key":"ref36","first-page":"3935","article-title":"Alternating minimizations converge to second-order optimal solutions","author":"li","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref35","first-page":"1246","article-title":"Gradient descent only converges to minimizers","author":"lee","year":"0","journal-title":"Conference on Learning Theory"},{"key":"ref34","first-page":"161","article-title":"The tradeoffs of large scale learning","author":"bottou","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"The landscape of empirical risk for non-convex losses","author":"mei","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2010.2051168"},{"key":"ref11","first-page":"2007","article-title":"Learning relus via gradient descent","author":"soltanolkotabi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Global optimality conditions for deep neural networks","author":"yun","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref13","article-title":"Over-parameterized deep neural networks have no strict local minima for any continuous activations","author":"li","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Learning deep models: Critical points and local openness","author":"nouiehed","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref15","first-page":"1","article-title":"Gradient descent with random initialization: Fast global convergence for nonconvex phase retrieval","author":"chen","year":"2018","journal-title":"Mathematical Programming"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2684758"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2399924"},{"key":"ref18","first-page":"1233","article-title":"No spurious local minima in nonconvex low rank problems: A unified geometric analysis","author":"ge","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70 JMLR org"},{"key":"ref19","first-page":"2441","article-title":"A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization","author":"josz","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"3873","article-title":"Global optimality of local search for low rank matrix recovery","author":"bhojanapalli","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"2057","article-title":"Matrix completion from noisy entries","volume":"11","author":"keshavan","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-017-9365-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2046205"},{"key":"ref6","first-page":"109","article-title":"A convergent gradient descent algorithm for rank minimization and semidefinite programming from random linear measurements","author":"zheng","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref29","first-page":"2973","article-title":"Matrix completion has no spurious local minimum","author":"ge","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2488608.2488693"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2598574"},{"key":"ref7","first-page":"559","article-title":"A nonconvex optimization framework for low rank matrix estimation","author":"zhao","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00120662"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/140979861"},{"journal-title":"Role of sparsity and structure in the optimization landscape of non-convex matrix sensing","year":"2020","author":"molybog","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2835403"},{"key":"ref22","article-title":"Sym-metry, saddle points, and global optimization landscape of nonconvex matrix factorization","author":"li","year":"2019","journal-title":"IEEE Transactions on Information Theory"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.29007\/3b2l","article-title":"Noisy matrix completion: understanding statistical guarantees for convex relaxation via nonconvex optimization","author":"chen","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/978-1-84800-155-8_7","article-title":"Graph implementations for nonsmooth convex programs","author":"grant","year":"2008","journal-title":"Recent Advances in Learning and Control Ser Lecture Notes in Control and Information Sciences"},{"key":"ref24","first-page":"5591","article-title":"How much restricted isometry is needed in nonconvex matrix recovery?","author":"zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"journal-title":"CVX Matlab Software for Disciplined Convex Programming Version 2 1","year":"2014","author":"grant","key":"ref41"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.29007\/shbv","article-title":"Nonconvex optimization meets low-rank matrix factorization: An overview","author":"chi","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-002-0347-5"},{"key":"ref26","first-page":"2351","article-title":"Complete dictionary recovery using nonconvex optimization","author":"sun","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1080\/10556789908805762"},{"journal-title":"Escaping from saddle points-online stochastic gradient for tensor decomposition","year":"2015","author":"ge","key":"ref25"}],"event":{"name":"2021 American Control Conference (ACC)","start":{"date-parts":[[2021,5,25]]},"location":"New Orleans, LA, USA","end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9482409\/9482614\/09483256.pdf?arnumber=9483256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T20:01:38Z","timestamp":1672948898000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9483256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,25]]},"references-count":44,"URL":"https:\/\/doi.org\/10.23919\/acc50511.2021.9483256","relation":{},"subject":[],"published":{"date-parts":[[2021,5,25]]}}}