{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T06:09:17Z","timestamp":1791266957592,"version":"4.1.0"},"reference-count":52,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00c3\u00adfico e Tecnol\u00c3\u00b3gico","doi-asserted-by":"publisher","award":["245358\/2012-9"],"award-info":[{"award-number":["245358\/2012-9"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Sci. Comput."],"published-print":{"date-parts":[[2017,1]]},"abstract":"<jats:p>Iterative hard thresholding (IHT) is a simple and effective approach to parsimonious data recovery. Its multilinear rank (mrank)-based application to low-rank tensor recovery (LRTR) is especially valuable given the difficulties involved in this problem. In this paper, we propose a novel IHT algorithm for LRTR, choosing sequential per-mode SVD truncation as its thresholding operator. This operator is less costly than those used in existing IHT algorithms for LRTR, and often leads to superior performance. Furthermore, by exploiting the sequential optimality of the employed modal projections, we derive recovery guarantees relying on restricted isometry constants. Though these guarantees are suboptimal, our numerical studies indicate that a quasi-optimal number of Gaussian measurements suffices for perfect data reconstruction. We also investigate a continuation technique which yields a sequence of progressively more complex estimated models until attaining a target mrank. When recovering real-world data, this strategy stabilizes the estimation error and can also accelerate convergence. In tensor completion, in particular, it can cope with nonideal characteristics of the sensed tensors and so is crucial for achieving a satisfactory performance. Extensive numerical experiments are reported, including the completion of hyperspectral imaging data and comparisons with several other existing approaches.<\/jats:p>","DOI":"10.1137\/16m1062089","type":"journal-article","created":{"date-parts":[[2017,5,23]],"date-time":"2017-05-23T11:55:26Z","timestamp":1495540526000},"page":"A860-A889","source":"Crossref","is-referenced-by-count":9,"title":["Low-Rank Tensor Recovery using Sequentially Optimal Modal Projections in Iterative Hard Thresholding (SeMPIHT)"],"prefix":"10.1137","volume":"39","author":[{"given":"Jos\u00e9 Henrique","family":"de Morais Goulart","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00e9rard","family":"Favier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2017,5,23]]},"reference":[{"key":"atypb1","doi-asserted-by":"publisher","DOI":"10.1007\/s00041-008-9035-z"},{"key":"atypb2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2042411"},{"key":"atypb3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"atypb4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2009.2035722"},{"key":"atypb5","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-009-9045-5"},{"key":"atypb6","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.858979"},{"key":"atypb7","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-012-9135-7"},{"key":"atypb8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9569-8_10"},{"key":"atypb9","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2009.01.014"},{"key":"atypb10","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2015.04.015"},{"key":"atypb11","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479896305696"},{"key":"atypb12","doi-asserted-by":"publisher","DOI":"10.1137\/06066518X"},{"key":"atypb13","doi-asserted-by":"publisher","DOI":"10.1007\/BF02288367"},{"key":"atypb14","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2015.03.012"},{"key":"atypb15","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4948-7"},{"key":"atypb16","volume-title":"Nuclear Norm of Higher-Order Tensors, preprint, https:\/\/arxiv.org\/abs\/1410.6072","author":"Friedland S.","year":"2014"},{"key":"atypb17","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/27\/2\/025010"},{"key":"atypb18","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9084-6"},{"key":"atypb19","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362674"},{"key":"atypb20","doi-asserted-by":"publisher","DOI":"10.1137\/090764189"},{"key":"atypb21","doi-asserted-by":"publisher","DOI":"10.1137\/130942401"},{"key":"atypb22","doi-asserted-by":"publisher","DOI":"10.1002\/gamm.201310004"},{"key":"atypb23","doi-asserted-by":"publisher","DOI":"10.1137\/090771806"},{"key":"atypb24","doi-asserted-by":"publisher","DOI":"10.1145\/2512329"},{"key":"atypb25","doi-asserted-by":"publisher","DOI":"10.1002\/sapm192761164"},{"key":"atypb26","first-page":"339","volume":"11","author":"Huang B.","year":"2015","journal-title":"Pacific J. Optim."},{"key":"atypb27","first-page":"937","volume-title":"Proceedings of the 23rd International Conference on Neural Information Processing Systems","author":"Jain P.","year":"2010"},{"key":"atypb28","volume-title":"Riemannian Preconditioning for Tensor Completion, preprint, https:\/\/arxiv.org\/abs\/1506.02159","author":"Kasai H.","year":"2015"},{"key":"atypb29","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"atypb30","doi-asserted-by":"publisher","DOI":"10.1190\/geo2013-0022.1"},{"key":"atypb31","doi-asserted-by":"publisher","DOI":"10.1007\/s10543-013-0455-z"},{"key":"atypb32","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-013-0434-7"},{"key":"atypb33","first-page":"2114","volume-title":"Proceedings of the 12th IEEE International Conference on Computer Vision","author":"Liu J.","year":"2009"},{"key":"atypb34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.39"},{"key":"atypb35","first-page":"73","volume-title":"Proceedings of the 31st International Conference on Machine Learning","author":"Mu C.","year":"2014"},{"key":"atypb36","first-page":"21","volume-title":"Proceedings of the 10th International Conference on Sampling Theory and Applications","author":"Rauhut H.","year":"2013"},{"key":"atypb37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16042-9_14"},{"key":"atypb38","volume-title":"Low Rank Tensor Recovery via Iterative Hard Thresholding, preprint, https:\/\/arxiv.org\/abs\/1602.05217","author":"Rauhut H.","year":"2016"},{"key":"atypb39","volume-title":"Tensor Theta Norms and Low Rank Recovery, preprint, https:\/\/arxiv.org\/abs\/1505.05175","author":"Rauhut H.","year":"2015"},{"key":"atypb40","doi-asserted-by":"publisher","DOI":"10.1137\/070697835"},{"key":"atypb41","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20227"},{"key":"atypb42","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2011.2151856"},{"key":"atypb43","doi-asserted-by":"publisher","DOI":"10.1137\/120876459"},{"key":"atypb44","volume-title":"Estimation of Low-Rank Tensors via Convex Optimization, preprint, https:\/\/arxiv.org\/abs\/1010.0789","author":"Tomioka R.","year":"2010"},{"key":"atypb45","volume-title":"NIPS Workshop on Tensors, Kernels, and Machine Learning","author":"Tomioka R.","year":"2010"},{"key":"atypb46","first-page":"972","volume-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems","author":"Tomioka R.","year":"2011"},{"key":"atypb47","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"atypb48","doi-asserted-by":"publisher","DOI":"10.1137\/110836067"},{"key":"atypb49","doi-asserted-by":"publisher","DOI":"10.3934\/ipi.2015.9.601"},{"key":"atypb50","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2420592"},{"key":"atypb51","volume-title":"On Tensor Completion via Nuclear Norm Minimization, preprint, https:\/\/arxiv.org\/abs\/1405.1773","author":"Yuan M.","year":"2014"},{"key":"atypb52","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2015.01.099"}],"container-title":["SIAM Journal on Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/16M1062089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:42:00Z","timestamp":1787326920000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/16M1062089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["10.1137\/16M1062089"],"URL":"https:\/\/doi.org\/10.1137\/16m1062089","relation":{},"ISSN":["1064-8275","1095-7197"],"issn-type":[{"value":"1064-8275","type":"print"},{"value":"1095-7197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1]]}}}