{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T03:25:49Z","timestamp":1791084349560,"version":"4.1.0"},"reference-count":44,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"5","funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-13-1-0492"],"award-info":[{"award-number":["N00014-13-1-0492"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-1016571"],"award-info":[{"award-number":["DMS-1016571"]}],"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-1527809"],"award-info":[{"award-number":["CCF-1527809"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Sci. Comput."],"published-print":{"date-parts":[[2016,1]]},"abstract":"<jats:p>Recovering matrices from compressive and grossly corrupted observations is a fundamental problem in robust statistics, with rich applications in computer vision and machine learning. In theory, under certain conditions, this problem can be solved in polynomial time via a natural convex relaxation, known as compressive principal component pursuit (CPCP). However, many existing provably convergent algorithms for CPCP suffer from superlinear per-iteration cost, which severely limits their applicability to large-scale problems. In this paper, we propose provably convergent, scalable, and efficient methods to solve, CPCP with (essentially) linear per-iteration cost. Our method combines classical ideas from Frank--Wolfe and proximal methods. In each iteration, we mainly exploit Frank--Wolfe to update the low-rank component with rank-one singular value decomposition and exploit the proximal step for the sparse term. Convergence results and implementation details are discussed. We demonstrate the practicability and scalability of our approach with numerical experiments on visual data.<\/jats:p>","DOI":"10.1137\/15m101628x","type":"journal-article","created":{"date-parts":[[2016,10,19]],"date-time":"2016-10-19T11:54:28Z","timestamp":1476878068000},"page":"A3291-A3317","source":"Crossref","is-referenced-by-count":49,"title":["Scalable Robust Matrix Recovery: Frank--Wolfe Meets Proximal Methods"],"prefix":"10.1137","volume":"38","author":[{"given":"Cun","family":"Mu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Wright","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donald","family":"Goldfarb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2016,10,19]]},"reference":[{"key":"atypb1","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iat002"},{"key":"atypb2","doi-asserted-by":"publisher","DOI":"10.1137\/090761793"},{"key":"atypb3","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"atypb4","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2010.5513535"},{"key":"atypb5","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2158250"},{"key":"atypb6","doi-asserted-by":"publisher","DOI":"10.1214\/12-AOS1000"},{"key":"atypb7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.282"},{"key":"atypb8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.120"},{"key":"atypb9","first-page":"703","volume-title":"Computer Vision---ACCV","author":"Wu L.","year":"2010"},{"key":"atypb10","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25240"},{"key":"atypb11","doi-asserted-by":"publisher","DOI":"10.1145\/1871437.1871475"},{"key":"atypb12","doi-asserted-by":"publisher","DOI":"10.1214\/11-AOS949"},{"key":"atypb13","volume-title":"Proceedings of the International Workshop on Computational Advances in Multi-Sensor Adaptive Processing","author":"Lin Z.","year":"2009"},{"key":"atypb14","volume-title":"The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices, preprint, https:\/\/arxiv.org\/abs\/1009.5055 arXiv:1009.5055","author":"Lin Z.","year":"2010"},{"key":"atypb15","first-page":"167","volume":"9","author":"Yuan X.","year":"2013","journal-title":"Pac. J. Optim."},{"key":"atypb16","volume-title":"Fast First-Order Methods for Stable Principal Component Pursuit, preprint, https:\/\/arxiv.org\/abs\/1105.2126 arXiv:1105.2126","author":"Aybat N. S.","year":"2011"},{"key":"atypb17","doi-asserted-by":"publisher","DOI":"10.1137\/100781894"},{"key":"atypb18","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-013-9613-0"},{"key":"atypb19","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-002-0347-5"},{"key":"atypb20","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"atypb21","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800030109"},{"key":"atypb22","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(66)90114-5"},{"key":"atypb23","first-page":"471","volume-title":"Proceedings of the 27th International Conference on Machine Learning","author":"Jaggi M.","year":"2010"},{"key":"atypb24","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-014-0778-9"},{"key":"atypb25","first-page":"427","volume":"28","author":"Jaggi M.","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"atypb26","volume-title":"Approximate Methods in Optimization Problems, Modern Analytic and Computational Methods in Science and Mathematics","author":"Demyanov V. F.","year":"1970"},{"key":"atypb27","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(78)90137-3"},{"key":"atypb28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00939668"},{"key":"atypb29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2002.808136"},{"key":"atypb30","doi-asserted-by":"publisher","DOI":"10.1145\/1824777.1824783"},{"key":"atypb31","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-014-0841-6"},{"key":"atypb32","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390191"},{"key":"atypb33","doi-asserted-by":"publisher","DOI":"10.1137\/090777761"},{"key":"atypb34","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-2012-02598-1"},{"key":"atypb35","doi-asserted-by":"publisher","DOI":"10.1137\/080738970"},{"key":"atypb36","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-009-0306-5"},{"key":"atypb37","first-page":"372","volume":"27","author":"Nesterov Y.","year":"1983","journal-title":"Soviet Math. Dokl."},{"key":"atypb38","volume-title":"Department of Computer Science","author":"Larsen R. M.","year":"1998"},{"key":"atypb39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.836169"},{"key":"atypb40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383258"},{"key":"atypb41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1177153"},{"key":"atypb42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.79"},{"key":"atypb43","doi-asserted-by":"publisher","DOI":"10.1109\/34.927464"},{"key":"atypb44","volume-title":"Proceedings of the 29th International Conference on Machine Learning, ACM","author":"Laue S.","year":"2012"}],"container-title":["SIAM Journal on Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/15M101628X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:26:44Z","timestamp":1787326004000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/15M101628X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1]]},"references-count":44,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2016,1]]}},"alternative-id":["10.1137\/15M101628X"],"URL":"https:\/\/doi.org\/10.1137\/15m101628x","relation":{},"ISSN":["1064-8275","1095-7197"],"issn-type":[{"value":"1064-8275","type":"print"},{"value":"1095-7197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1]]}}}