{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T11:41:46Z","timestamp":1784288506737,"version":"3.55.0"},"reference-count":220,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"20","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-18-1-2142"],"award-info":[{"award-number":["N00014-18-1-2142"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-19-1-2404"],"award-info":[{"award-number":["N00014-19-1-2404"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-18-1-0303"],"award-info":[{"award-number":["W911NF-18-1-0303"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-15-1-0205"],"award-info":[{"award-number":["FA9550-15-1-0205"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1901199"],"award-info":[{"award-number":["CCF-1901199"]}],"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-1806154"],"award-info":[{"award-number":["CCF-1806154"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-1818571"],"award-info":[{"award-number":["ECCS-1818571"]}],"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-1718698"],"award-info":[{"award-number":["CCF-1718698"]}],"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-1910410"],"award-info":[{"award-number":["CCF-1910410"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Harvard Dean's Competitive Fund for Promising Research"},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"crossref","award":["YIP FA9550-19-1-0030"],"award-info":[{"award-number":["YIP FA9550-19-1-0030"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ARO","award":["W911NF-18-1-0303"],"award-info":[{"award-number":["W911NF-18-1-0303"]}]},{"name":"ONR","award":["N00014-19-1-2120"],"award-info":[{"award-number":["N00014-19-1-2120"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1907661"],"award-info":[{"award-number":["CCF-1907661"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1900140"],"award-info":[{"award-number":["IIS-1900140"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1109\/tsp.2019.2937282","type":"journal-article","created":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T19:50:25Z","timestamp":1566589825000},"page":"5239-5269","source":"Crossref","is-referenced-by-count":266,"title":["Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview"],"prefix":"10.1109","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6766-5459","authenticated-orcid":false,"given":"Yuejie","family":"Chi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5174-2595","authenticated-orcid":false,"given":"Yue M.","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9256-5815","authenticated-orcid":false,"given":"Yuxin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-005-0179-9"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1026-2"},{"key":"ref171","article-title":"Gradient descent efficiently finds the cubic-regularized non-convex newton step","author":"carmon","year":"2016"},{"key":"ref174","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate $o(1\/k^2)$","volume":"269","author":"nesterov","year":"1983","journal-title":"Dokl Akad Nauk SSSR"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1137\/17M1114296"},{"key":"ref176","article-title":"The power of normalization: Faster evasion of saddle points","author":"levy","year":"2016"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1145\/3055399.3055464"},{"key":"ref178","first-page":"1042","article-title":"Accelerated gradient descent escapes saddle points faster than gradient descent","author":"jin","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref177","first-page":"1724","article-title":"How to escape saddle points efficiently","author":"jin","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-006-0706-8"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719857"},{"key":"ref39","article-title":"Symmetry, saddle points, and global geometry of nonconvex matrix factorization","author":"li","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/78.365290"},{"key":"ref33","article-title":"Nonconvex optimization meets low-rank matrix factorization: An overview","author":"chi","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iay003"},{"key":"ref31","first-page":"3873","article-title":"Global optimality of local search for low rank matrix recovery","author":"bhojanapalli","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"2973","article-title":"Matrix completion has no spurious local minimum","author":"ge","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/72.392248"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90014-2"},{"key":"ref35","volume":"87","author":"nesterov","year":"2013","journal-title":"Introductory Lectures on Convex Optimization A Basic Course"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974997"},{"key":"ref181","first-page":"3716","author":"allen-zhu","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref180","first-page":"5530","article-title":"First-order stochastic algorithms for escaping from saddle points in almost linear time","author":"xu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0738-9"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2745623"},{"key":"ref183","first-page":"6086","article-title":"Convolutional phase retrieval","author":"qu","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref182","article-title":"Recent advances in stochastic convex and non-convex optimization","author":"allen-zhu","year":"2017","journal-title":"ICML Tut"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2019.02.001"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01364-5"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19749-4_2"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2015.07.007"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-017-9365-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09429-9"},{"key":"ref179","first-page":"2675","article-title":"Natasha 2: Faster non-convex optimization than SGD","author":"allen-zhu","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref29","first-page":"2351","article-title":"Complete dictionary recovery using nonconvex optimization","author":"sun","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2598574"},{"key":"ref22","article-title":"Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees","author":"chen","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21638"},{"key":"ref24","first-page":"964","article-title":"Low-rank solutions of linear matrix equations via Procrustes flow","author":"tu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2018.01.001"},{"key":"ref26","first-page":"1107","article-title":"Non-convex robust PCA","author":"netrapalli","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","first-page":"1022","article-title":"Provable non-convex phase retrieval with outliers: Median truncated Wirtinger flow","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1137\/17M1124097"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2826566"},{"key":"ref154","first-page":"5586","article-title":"How much restricted isometry is needed in nonconvex matrix recovery?","author":"zhang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref153","article-title":"Sharp restricted isometry bounds for the inexistence of spurious local minima in nonconvex matrix recovery","author":"zhang","year":"2019"},{"key":"ref156","first-page":"65","article-title":"Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach","author":"park","year":"0","journal-title":"Proc Artif Intell Statist"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOS1637"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-013-9162-z"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2632149"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2632162"},{"key":"ref146","first-page":"2","article-title":"Algorithmic regularization in over-parameterized matrix sensing and neural networks with quadratic activations","author":"li","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref147","article-title":"Implicit regularization and solution uniqueness in over-parameterized matrix sensing","author":"kyrillidis","year":"2018"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2089624"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1007\/s00041-013-9305-2"},{"key":"ref59","first-page":"1496","article-title":"Nonconvex matrix factorization from rank-one measurements","volume":"89","author":"li","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s00025-016-0564-5"},{"key":"ref57","article-title":"Algorithms and theory for clustering and nonconvex quadratic programming","author":"soltanolkotabi","year":"2014"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794308.006"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1561\/2200000048"},{"key":"ref54","first-page":"530","article-title":"Dropping convexity for faster semi-definite optimization","author":"bhojanapalli","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref53","article-title":"A convergent gradient descent algorithm for rank minimization and semidefinite programming from random linear measurements","author":"zheng","year":"2015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/BF02294053"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2835403"},{"key":"ref167","first-page":"605","article-title":"Globally optimal gradient descent for a ConvNet with Gaussian inputs","author":"brutzkus","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref166","first-page":"2252","article-title":"Efficient dictionary learning with gradient descent","author":"gilboa","year":"0","journal-title":"Proc ICML Workshop Modern Trends Nonconvex Optim Mach Learn"},{"key":"ref165","first-page":"1067","article-title":"Gradient descent can take exponential time to escape saddle points","author":"du","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref164","first-page":"3935","article-title":"Alternating minimizations converge to second-order optimal solutions","author":"li","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref163","first-page":"2014","article-title":"Gradient primal-dual algorithm converges to second-order stationary solution for nonconvex distributed optimization over networks","author":"hong","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01374-3"},{"key":"ref161","first-page":"1246","article-title":"Gradient descent only converges to minimizers","author":"lee","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref160","article-title":"When are nonconvex optimization problems not scary?","author":"sun","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2352673"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2821706"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/31\/11\/115002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2294644"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"ref159","first-page":"797","article-title":"Escaping from saddle points-online stochastic gradient for tensor decomposition","author":"ge","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/090761793"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1364\/OE.20.008296"},{"key":"ref157","first-page":"316","article-title":"Exponentially many local minima for single neurons","author":"auer","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2010.02.001"},{"key":"ref158","first-page":"4430","article-title":"Spurious local minima are common in two-layer ReLU neural networks","author":"safran","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","article-title":"Phase retrieval: An overview of recent developments","author":"jaganathan","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21432"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1214\/14-AOS1267"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2429594"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2111771"},{"key":"ref41","article-title":"The global optimization geometry of shallow linear neural networks","volume":"170","author":"zhu","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1364\/AO.21.002758"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2008.03.014"},{"key":"ref73","article-title":"Entrywise eigenvector analysis of random matrices with low expected rank","author":"abbe","year":"2017"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1745"},{"key":"ref71","first-page":"1","article-title":"The likelihood ratio test in high-dimensional logistic regression is asymptotically a rescaled chi-square","author":"sur","year":"2017","journal-title":"Probability Theory Related Fields"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1137\/17M1122025"},{"key":"ref76","article-title":"Noisy matrix completion: Understanding statistical guarantees for convex relaxation via nonconvex optimization","author":"chen","year":"2019"},{"key":"ref77","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.1910053116","article-title":"Inference and uncertainty quantification for noisy matrix completion","author":"chen","year":"2019"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01363-6"},{"key":"ref75","article-title":"The leave-one-out approach for matrix completion: Primal and dual analysis","author":"ding","year":"2018"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2891653"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1214\/16-AOS1443"},{"key":"ref60","first-page":"1","article-title":"Regularized gradient descent: A non-convex recipe for fast joint blind deconvolution and demixing","volume":"8","author":"ling","year":"2018","journal-title":"Inf Inference"},{"key":"ref62","article-title":"Convergence analysis for rectangular matrix completion using Burer-Monteiro factorization and gradient descent","author":"zheng","year":"2016"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2864660"},{"key":"ref63","first-page":"4152","article-title":"Fast algorithms for robust PCA via gradient descent","author":"yi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","first-page":"2057","article-title":"Matrix completion from noisy entries","volume":"11","author":"keshavan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1137\/17M1151390"},{"key":"ref66","article-title":"Nonconvex rectangular matrix completion via gradient descent without $\\ell _{2,\\infty }$ regularization","author":"chen","year":"2019"},{"key":"ref67","first-page":"1","article-title":"A bound for the error in the normal approximation to the distribution of a sum of dependent random variables","author":"stein","year":"0","journal-title":"Proc Berkeley Symp on Math Statist and Prob"},{"key":"ref68","author":"chen","year":"2010","journal-title":"Normal Approximation by Stein's Method"},{"key":"ref69","first-page":"1","article-title":"On the impact of predictor geometry on the performance on high-dimensional ridge-regularized generalized robust regression estimators","author":"karoui","year":"2015","journal-title":"Probability Theory Related Fields"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2249572"},{"key":"ref198","first-page":"797","article-title":"Nearly optimal robust matrix completion","author":"cherapanamjeri","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref199","first-page":"600","article-title":"Low-rank and sparse structure pursuit via alternating minimization","author":"gu","year":"0","journal-title":"Proc Artif Intell Statist"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1214\/11-AOS894"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2415195"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/SAMPTA.2017.8024387"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2010.5513538"},{"key":"ref95","first-page":"1","article-title":"Local convergence of an algorithm for subspace identification from partial data","author":"balzano","year":"2014","journal-title":"Found Comput Math"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1137\/15M1050525"},{"key":"ref190","first-page":"5857","article-title":"A primal-dual analysis of global optimality in nonconvex low-rank matrix recovery","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2171521"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2104999"},{"key":"ref92","author":"absil","year":"2009","journal-title":"Optimization Algorithms on Matrix Manifolds"},{"key":"ref192","first-page":"1665","article-title":"Restricted strong convexity and weighted matrix completion: Optimal bounds with noise","volume":"98888","author":"negahban","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479895290954"},{"key":"ref90","article-title":"The nonsmooth landscape of phase retrieval","author":"davis","year":"2017"},{"key":"ref98","article-title":"On critical points of quadratic low-rank matrix optimization problems","author":"uschmajew","year":"2018"},{"key":"ref99","article-title":"Solving systems of phaseless equations via Riemannian optimization with optimal sampling complexity","author":"cai","year":"2018"},{"key":"ref96","article-title":"Guarantees of Riemannian optimization for low rank matrix completion","author":"wei","year":"2016"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1137\/110845768"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1137\/120893707"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2771733"},{"key":"ref84","first-page":"4917","article-title":"Fast, sample-efficient algorithms for structured phase retrieval","author":"jagatap","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2401574"},{"key":"ref80","first-page":"272","article-title":"Efficient projections onto the $\\ell _1$-ball for learning in high dimensions","author":"duchi","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref89","first-page":"1","article-title":"A nonconvex approach for phase retrieval: Reshaped Wirtinger flow and incremental algorithms","volume":"18","author":"zhang","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref85","article-title":"Phase retrieval via incremental truncated Wirtinger flow","author":"kolte","year":"2016"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2756858"},{"key":"ref87","article-title":"Nonconvex low-rank matrix recovery with arbitrary outliers via median-truncated gradient descent","author":"li","year":"2017"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1975-0367131-6"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1137\/17M1141394"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719574"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/bs.hna.2018.09.001"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2017.8335189"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/SAMPTA.2017.8024422"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/CoSeRa.2016.7745690"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2343623"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2277451"},{"key":"ref207","first-page":"3653","article-title":"On the optimization landscape of tensor decompositions","author":"ge","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21861"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2601599"},{"key":"ref206","first-page":"613","article-title":"Alternating minimization for mixed linear regression","author":"yi","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref211","first-page":"597","article-title":"Convergence analysis of two-layer neural networks with ReLU activation","author":"li","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref210","first-page":"4140","article-title":"Recovery guarantees for one-hidden-layer neural networks","author":"zhong","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2935447"},{"key":"ref213","article-title":"Local geometry of one-hidden-layer neural networks for logistic regression","author":"fu","year":"2018"},{"key":"ref214","article-title":"A selective overview of deep learning","author":"fan","year":"2019"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-002-0352-8"},{"key":"ref216","first-page":"3243","article-title":"Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form","author":"bhojanapalli","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref217","first-page":"361","article-title":"On the low-rank approach for semidefinite programs arising in synchronization and community detection","author":"bandeira","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref218","year":"0"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1561\/2200000058"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682568"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-4549-5"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/BF01932678"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1973-0348991-3"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1137\/0707001"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-018-9395-y"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8007083"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2904918"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1214\/11-AOS887"},{"key":"ref134","first-page":"1","article-title":"Community detection and stochastic block models: Recent developments","volume":"18","author":"abbe","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1992.10476258"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/1219092.1219097"},{"key":"ref136","first-page":"371","article-title":"Spectral MLE: Top-$k$ rank aggregation from pairwise comparisons","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2016.1534"},{"key":"ref138","article-title":"Sparse and low-rank tensor estimation via cubic sketchings","author":"hao","year":"2018"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21748"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2841377"},{"key":"ref140","article-title":"Nonconvex low-rank symmetric tensor completion from noisy data","author":"cai","year":"2019","journal-title":"accept Neural Info Process Sys"},{"key":"ref141","first-page":"2933","article-title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","author":"dauphin","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref142","first-page":"81","article-title":"Efficient approaches for escaping higher order saddle points in non-convex optimization","author":"anandkumar","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref143","first-page":"1233","article-title":"No spurious local minima in nonconvex low rank problems: A unified geometric analysis","author":"ge","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2539100"},{"key":"ref144","article-title":"Memory-efficient kernel PCA via partial matrix sampling and nonconvex optimization: A model-free analysis of local minima","author":"chen","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-009-9045-5"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503198"},{"key":"ref109","first-page":"559","author":"zhao","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref108","first-page":"638","article-title":"Fast matrix completion without the condition number","author":"hardt","year":"0","journal-title":"Proceedings of The 27th Conference on Learning Theory"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.75"},{"key":"ref106","article-title":"Efficient algorithms for collaborative filtering","author":"keshavan","year":"2012"},{"key":"ref105","first-page":"3367","article-title":"Matrix completion and low-rank SVD via fast alternating least squares","volume":"16","author":"hastie","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref104","first-page":"237","article-title":"A practical algorithm for the determination of phase from image and diffraction plane pictures","volume":"35","author":"gerchberg","year":"1972","journal-title":"Optik"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2800663"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2448516"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2773497"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1137\/090771806"},{"key":"ref110","first-page":"937","article-title":"Guaranteed rank minimization via singular value projection","author":"jain","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2600566"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21760"},{"key":"ref12","article-title":"Matrix rank minimization with applications","author":"fazel","year":"2002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/070697835"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2044061"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.52"},{"key":"ref118","article-title":"Composite optimization for robust blind deconvolution","author":"charisopoulos","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2046205"},{"key":"ref117","article-title":"Low-rank matrix recovery with composite optimization: Good conditioning and rapid convergence","author":"charisopoulos","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2488608.2488693"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2399924"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1306110110"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2054251"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1137\/120876459"},{"key":"ref116","article-title":"Stochastic methods for composite optimization problems","author":"duchi","year":"2017"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iay015"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2893254"},{"key":"ref121","first-page":"3371","article-title":"Approximate message passing for amplitude based optimization","author":"ma","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref122","article-title":"Coordinate descent algorithms for phase retrieval","author":"zeng","year":"2017"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2855667"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/78\/8834988\/8811622-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/8834988\/08811622.pdf?arnumber=8811622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:55Z","timestamp":1649443735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8811622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":220,"journal-issue":{"issue":"20"},"URL":"https:\/\/doi.org\/10.1109\/tsp.2019.2937282","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,15]]}}}