{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:28:22Z","timestamp":1772908102569,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61663049"],"award-info":[{"award-number":["61663049"]}],"id":[{"id":"10.13039\/501100001809","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":[[2022,10,1]]},"DOI":"10.1109\/tpami.2021.3085858","type":"journal-article","created":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T21:41:48Z","timestamp":1622583708000},"page":"6153-6168","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Low-Rank Semidefinite Programming With Robust Loss Functions"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8944-8618","authenticated-orcid":false,"given":"Quanming","family":"Yao","sequence":"first","affiliation":[{"name":"4Paradigm Inc, Beijing, China"}]},{"given":"Hansi","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7398-2285","authenticated-orcid":false,"given":"En-Liang","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Yunnan Normal University, Kunming, Yunnan Province, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4828-8248","authenticated-orcid":false,"given":"James T.","family":"Kwok","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2285514"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v084.i10"},{"key":"ref71","first-page":"847","article-title":"An inverse power method for nonlinear eigenproblems with applications in 1-spectral clustering and sparse PCA","author":"hein","year":"2010","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927819"},{"key":"ref39","first-page":"1297","article-title":"Learning from crowds","volume":"11","author":"raykar","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5124-8"},{"key":"ref33","first-page":"530","article-title":"Dropping convexity for faster semi-definite optimization","author":"bhojanapalli","year":"2016","journal-title":"Proc Conf Learn Theory"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2651816"},{"key":"ref31","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":"ref30","first-page":"1410","article-title":"Practical low-rank matrix approximation under robust $\\ell _1$?1-norm","author":"zheng","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1023\/A:1023709501986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref34","first-page":"2287","article-title":"Smoothed analysis of the low-rank approach for smooth semidefinite programs","author":"pumir","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref60","first-page":"1081","article-title":"Analysis of multi-stage convex relaxation for sparse regularization","volume":"11","author":"zhang","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/83.392335"},{"key":"ref61","first-page":"37","article-title":"A general iterative shrinkage and thresholding algorithm for non-convex regularized optimization problems","author":"gong","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2008.927346"},{"key":"ref28","author":"nocedal","year":"2006","journal-title":"Numerical Optimization"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971309"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21830"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273542"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"2117","DOI":"10.1109\/TNN.2011.2172457","article-title":"Symmetric nonnegative matrix factorization: Algorithms and applications to probabilistic clustering","volume":"22","author":"he","year":"2011","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref29","first-page":"1257","article-title":"Probabilistic matrix factorization","author":"mnih","year":"2008","journal-title":"Proc 20th Int Conf Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2731321"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-014-0247-2"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858249"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/1038003"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/0806020"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s12532-015-0082-6","article-title":"SDPNAL+: A majorized semismooth newton-CG augmented lagrangian method for semidefinite programming with nonnegative constraints","volume":"7","author":"toh","year":"2015","journal-title":"Math Program Comput"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-004-0564-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-002-0352-8"},{"key":"ref24","first-page":"530","article-title":"Dropping convexity for faster semidefinite optimization","author":"srinadh","year":"2016","journal-title":"Proc Conf Learn Theory"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/080731359"},{"key":"ref26","first-page":"2765","article-title":"The non-convex burer-monteiro approach works on smooth semidefinite programs","author":"boumal","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref25","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":"Proc Int Conf Neural Inf Process"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1137\/110836936"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/462"},{"key":"ref58","first-page":"1458","article-title":"Convergence rates of inexact proximal-gradient methods for convex optimization","author":"schmidt","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref57","first-page":"379","article-title":"Accelerated proximal gradient methods for nonconvex programming","author":"li","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref56","first-page":"209","article-title":"BCDNPKL: Scalable non-parametric kernel learning using block coordinate descent","author":"hu","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1109\/TNNLS.2014.2312535","article-title":"Efficient $\\ell _{1}$?1-norm-based low-rank matrix approximations for large-scale problems using alternating rectified gradient method","volume":"26","author":"kim","year":"2015","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-8815-7"},{"key":"ref53","first-page":"783","article-title":"Optimization with first-order surrogate functions","author":"mairal","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/349"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5158-y"},{"key":"ref11","first-page":"235","article-title":"Fast low-rank semidefinite programming for embedding and clustering","author":"kulis","year":"2007","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7637-6_28"},{"key":"ref12","first-page":"1","article-title":"Exact clustering of weighted graphs via semidefinite programming","volume":"20","author":"pirinen","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1137\/050645506","article-title":"A direct formulation for sparse PCA using semidefinite programming","volume":"49","author":"d'aspremont","year":"2007","journal-title":"SIAM Rev"},{"key":"ref14","first-page":"899","article-title":"Truncated power method for sparse eigenvalue problems","volume":"14","author":"yuan","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2846588"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015345"},{"key":"ref17","first-page":"1385","article-title":"Colored maximum variance unfolding","author":"song","year":"2008","journal-title":"Proc 20th Int Conf Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390229"},{"key":"ref19","first-page":"1313","article-title":"A family of simple non-parametric kernel learning algorithms","volume":"12","author":"zhuang","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/2400000009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref6","first-page":"427","article-title":"Revisiting frank-wolfe: Projection-free sparse convex optimization","author":"jaggi","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","first-page":"177","article-title":"A hybrid algorithm for convex semidefinite optimization","author":"laue","year":"2012","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","first-page":"2762","article-title":"Deterministic symmetric positive semidefinite matrix completion","author":"bishop","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1198\/0003130042836"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2014.03.015"},{"key":"ref9","first-page":"1349","article-title":"Active positive semidefinite matrix completion: Algorithms, theory and applications","author":"bhargava","year":"2017","journal-title":"Proc 20th Int Conf Artif Intell Statist"},{"key":"ref46","first-page":"3590","article-title":"Robust dictionary learning with capped $\\ell _1$?1-norm","author":"jiang","year":"2015","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref45","first-page":"771","article-title":"Efficient computation of robust low-rank matrix approximations in the presence of missing data using the $\\ell _1$?1-norm","author":"eriksson","year":"2010","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10618600.2000.10474858","article-title":"Optimization transfer using surrogate objective functions","volume":"9","author":"lange","year":"2000","journal-title":"J Comput Graph Statist"},{"key":"ref47","first-page":"6574","article-title":"Efficient learning with a family of nonconvex regularizers by redistributing nonconvexity","volume":"18","author":"yao","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.60"},{"key":"ref41","first-page":"5061","article-title":"Scalable robust matrix factorization with nonconvex loss","author":"yao","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s00041-008-9045-x"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOS729"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9893034\/09444847.pdf?arnumber=9444847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:17:29Z","timestamp":1725149849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9444847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":73,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3085858","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}