{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T00:54:34Z","timestamp":1768006474196,"version":"3.49.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T00:00:00Z","timestamp":1667001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T00:00:00Z","timestamp":1667001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["(448293816; 211504053 - SFB 1060)"],"award-info":[{"award-number":["(448293816; 211504053 - SFB 1060)"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["(KR 4512\/2-2)"],"award-info":[{"award-number":["(KR 4512\/2-2)"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013296","name":"Max Planck Institute for Mathematics in the Sciences","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100013296","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Numer Algor"],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this paper, we present modifications of the iterative hard thresholding (IHT) method for recovery of jointly row-sparse and low-rank matrices. In particular, a Riemannian version of IHT is considered which significantly reduces computational cost of the gradient projection in the case of rank-one measurement operators, which have concrete applications in blind deconvolution. Experimental results are reported that show near-optimal recovery for Gaussian and rank-one measurements, and that adaptive stepsizes give crucial improvement. A Riemannian proximal gradient method is derived for the special case of unknown sparsity.<\/jats:p>","DOI":"10.1007\/s11075-022-01433-5","type":"journal-article","created":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T13:11:39Z","timestamp":1667049099000},"page":"669-693","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Riemannian thresholding methods for row-sparse and low-rank matrix recovery"],"prefix":"10.1007","volume":"93","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0732-5719","authenticated-orcid":false,"given":"Henrik","family":"Eisenmann","sequence":"first","affiliation":[]},{"given":"Felix","family":"Krahmer","sequence":"additional","affiliation":[]},{"given":"Max","family":"Pfeffer","sequence":"additional","affiliation":[]},{"given":"Andr\u00e9","family":"Uschmajew","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"1433_CR1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400830244","volume-title":"Optimization algorithms on matrix manifolds","author":"P-A Absil","year":"2008","unstructured":"Absil, P.-A., Mahony, R., Sepulchre, R.: Optimization algorithms on matrix manifolds. Princeton University Press, Princeton (2008)"},{"issue":"1","key":"1433_CR2","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1137\/100802529","volume":"22","author":"P-A Absil","year":"2012","unstructured":"Absil, P.-A., Malick, J.: Projection-like retractions on matrix manifolds. SIAM J. Optim. 22(1), 135\u2013158 (2012)","journal-title":"SIAM J. Optim."},{"issue":"3","key":"1433_CR3","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1109\/TIT.2013.2294644","volume":"60","author":"A Ahmed","year":"2014","unstructured":"Ahmed, A., Recht, B., Romberg, J.: Blind deconvolution using convex programming. IEEE Trans. Inform. Theory 60(3), 1711\u20131732 (2014)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"3","key":"1433_CR4","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1093\/imaiai\/iaw012","volume":"5","author":"S Bahmani","year":"2016","unstructured":"Bahmani, S., Romberg, J.: Near-optimal estimation of simultaneously sparse and low-rank matrices from nested linear measurements. Inf. Inference 5(3), 331\u2013351 (2016)","journal-title":"Inf. Inference"},{"key":"1433_CR5","unstructured":"Beck, A.: First-order methods in optimization. PA; Mathematical Optimization Society, Philadelphia, PA, Society for Industrial and Applied Mathematics (SIAM), Philadelphia (2017)"},{"key":"1433_CR6","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/j.acha.2021.10.002","volume":"56","author":"J-F Cai","year":"2022","unstructured":"Cai, J.-F., Li, J., Lu, X., You, J.: Sparse signal recovery from phaseless measurements via hard thresholding pursuit. Appl. Comput. Harmon. Anal. 56, 367\u2013390 (2022)","journal-title":"Appl. Comput. Harmon. Anal."},{"issue":"2","key":"1433_CR7","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1109\/TIT.2005.862083","volume":"52","author":"EJ Cand\u00e8s","year":"2006","unstructured":"Cand\u00e8s, E.J., Romberg, J., Tao, T.: Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inform. Theory 52(2), 489\u2013509 (2006)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"1","key":"1433_CR8","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1137\/18M122457X","volume":"30","author":"S Chen","year":"2020","unstructured":"Chen, S., Ma, S., So, A.M.-C., Zhang, T.: Proximal gradient method for nonsmooth optimization over the Stiefel manifold. SIAM J. Optim. 30(1), 210\u2013239 (2020)","journal-title":"SIAM J. Optim."},{"issue":"4","key":"1433_CR9","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","volume":"52","author":"DL Donoho","year":"2006","unstructured":"Donoho, D.L.: Compressed sensing. IEEE Trans. Inform. Theory 52(4), 1289\u20131306 (2006)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"3","key":"1433_CR10","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1016\/j.acha.2013.08.003","volume":"36","author":"YC Eldar","year":"2014","unstructured":"Eldar, Y.C., Mendelson, S.: Phase retrieval: stability and recovery guarantees. Appl. Comput. Harmon. Anal. 36(3), 473\u2013494 (2014)","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"1433_CR11","volume":"392","author":"M Fornasier","year":"2021","unstructured":"Fornasier, M., Maly, J., Naumova, V.: Robust recovery of low-rank matrices with non-orthogonal sparse decomposition from incomplete measurements. Appl. Math. Comput. 392, 125702 (2021)","journal-title":"Appl. Math. Comput."},{"issue":"1","key":"1433_CR12","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1142\/S0219530519410094","volume":"18","author":"S Foucart","year":"2020","unstructured":"Foucart, S., Gribonval, R., Jacques, L., Rauhut, H.: Jointly low-rank and bisparse recovery: questions and partial answers. Anal. Appl. (Singap.) 18(1), 25\u201348 (2020)","journal-title":"Anal. Appl. (Singap.)"},{"key":"1433_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4948-7","volume-title":"A Mathematical Introduction to Compressive Sensing","author":"S Foucart","year":"2013","unstructured":"Foucart, S., Rauhut, H.: A mathematical introduction to compressive sensing. Birkh\u00e4user\/Springer, New York (2013)"},{"issue":"3","key":"1433_CR14","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1007\/s10444-019-09698-6","volume":"45","author":"J Geppert","year":"2019","unstructured":"Geppert, J., Krahmer, F., St\u00f6ger, D.: Sparse power factorization: balancing peakiness and sample complexity. Adv. Comput. Math. 45(3), 1711\u20131728 (2019)","journal-title":"Adv. Comput. Math."},{"issue":"6","key":"1433_CR15","doi-asserted-by":"publisher","first-page":"1468","DOI":"10.1109\/TPAMI.2019.2900306","volume":"42","author":"BD Haeffele","year":"2020","unstructured":"Haeffele, B.D., Vidal, R.: Structured low-rank matrix factorization: global optimality, algorithms, and applications. IEEE Trans. Pattern Anal. Mach. Intell. 42(6), 1468\u20131482 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1433_CR16","doi-asserted-by":"crossref","unstructured":"Huang, W., Wei, K.: Riemannian proximal gradient methods. Math. Program. 194(1-2, Ser. A), 371\u2013413 (2022)","DOI":"10.1007\/s10107-021-01632-3"},{"issue":"1","key":"1433_CR17","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.acha.2015.06.007","volume":"42","author":"M Iwen","year":"2017","unstructured":"Iwen, M., Viswanathan, A., Wang, Y.: Robust sparse phase retrieval made easy. Appl. Comput. Harmon. Anal. 42(1), 135\u2013142 (2017)","journal-title":"Appl. Comput. Harmon. Anal."},{"issue":"2","key":"1433_CR18","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1109\/TIT.2017.2784481","volume":"64","author":"P Jung","year":"2018","unstructured":"Jung, P., Krahmer, F., St\u00f6ger, D.: Blind demixing and deconvolution at near-optimal rate. IEEE Trans. Inform. Theory 64(2), 704\u2013727 (2018)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"1","key":"1433_CR19","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1137\/16M1067469","volume":"1","author":"M Kech","year":"2017","unstructured":"Kech, M., Krahmer, F.: Optimal injectivity conditions for bilinear inverse problems with applications to identifiability of deconvolution problems. SIAM J. Appl. Algebra Geom. 1(1), 20\u201337 (2017)","journal-title":"SIAM J. Appl. Algebra Geom."},{"key":"1433_CR20","doi-asserted-by":"crossref","unstructured":"Kliesch, M., Szarek, S.J., Jung, P.: Simultaneous structures in convex signal recovery \u2013 revisiting the convex combination of norms. Front. Appl. Math. Stat. 5 (2019)","DOI":"10.3389\/fams.2019.00023"},{"issue":"4","key":"1433_CR21","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1002\/cpa.21957","volume":"74","author":"F Krahmer","year":"2021","unstructured":"Krahmer, F., St\u00f6ger, D.: On the convex geometry of blind deconvolution and matrix completion. Comm. Pure Appl. Math. 74(4), 790\u2013832 (2021)","journal-title":"Comm. Pure Appl. Math."},{"issue":"3","key":"1433_CR22","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.1109\/TIT.2017.2784479","volume":"64","author":"K Lee","year":"2018","unstructured":"Lee, K., Wu, Y., Bresler, Y.: Near-optimal compressed sensing of a class of sparse low-rank matrices via sparse power factorization. IEEE Trans. Inform. Theory 64(3), 1666\u20131698 (2018)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"3","key":"1433_CR23","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1016\/j.acha.2018.01.001","volume":"47","author":"X Li","year":"2019","unstructured":"Li, X., Ling, S., Strohmer, T., Wei, K.: Rapid, robust, and reliable blind deconvolution via nonconvex optimization. Appl. Comput. Harmon. Anal. 47(3), 893\u2013934 (2019)","journal-title":"Appl. Comput. Harmon. Anal."},{"issue":"7","key":"1433_CR24","doi-asserted-by":"publisher","first-page":"4266","DOI":"10.1109\/TIT.2016.2569578","volume":"62","author":"Y Li","year":"2016","unstructured":"Li, Y., Lee, K., Bresler, Y.: Identifiability in blind deconvolution with subspace or sparsity constraints. IEEE Trans. Inform. Theory 62(7), 4266\u20134275 (2016)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"7","key":"1433_CR25","doi-asserted-by":"publisher","first-page":"4497","DOI":"10.1109\/TIT.2017.2701342","volume":"63","author":"S Ling","year":"2017","unstructured":"Ling, S., Strohmer, T.: Blind deconvolution meets blind demixing: algorithms and performance bounds. IEEE Trans. Inform. Theory 63(7), 4497\u20134520 (2017)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"1","key":"1433_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/imaiai\/iax022","volume":"8","author":"S Ling","year":"2019","unstructured":"Ling, S., Strohmer, T.: Regularized gradient descent: a non-convex recipe for fast joint blind deconvolution and demixing. Inf. Inference 8(1), 1\u201349 (2019)","journal-title":"Inf. Inference"},{"key":"1433_CR27","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.ipl.2017.05.008","volume":"126","author":"M Magdon-Ismail","year":"2017","unstructured":"Magdon-Ismail, M.: NP-hardness and inapproximability of sparse PCA. Inform. Process. Lett. 126, 35\u201338 (2017)","journal-title":"Inform. Process. Lett."},{"key":"1433_CR28","unstructured":"Maly, J.: Robust sensing of low-rank matrices with non-orthogonal sparse decomposition. arXiv:2103.05523 (2021)"},{"issue":"5","key":"1433_CR29","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.1109\/TIT.2015.2401574","volume":"61","author":"S Oymak","year":"2015","unstructured":"Oymak, S., Jalali, A., Fazel, M., Eldar, Y.C., Hassibi, B.: Simultaneously structured models with application to sparse and low-rank matrices. IEEE Trans. Inform. Theory 61(5), 2886\u20132908 (2015)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"3","key":"1433_CR30","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1561\/2400000003","volume":"1","author":"N Parikh","year":"2014","unstructured":"Parikh, N., Boyd, S.: Proximal algorithms. Foundations and Trends in Optimization 1(3), 127\u2013239 (2014)","journal-title":"Foundations and Trends in Optimization"},{"issue":"1","key":"1433_CR31","doi-asserted-by":"publisher","first-page":"622","DOI":"10.1137\/140957822","volume":"25","author":"R Schneider","year":"2015","unstructured":"Schneider, R., Uschmajew, A.: Convergence results for projected line-search methods on varieties of low-rank matrices via \u0141ojasiewicz inequality. SIAM J. Optim. 25(1), 622\u2013646 (2015)","journal-title":"SIAM J. Optim."},{"issue":"4","key":"1433_CR32","doi-asserted-by":"publisher","first-page":"2374","DOI":"10.1109\/TIT.2019.2891653","volume":"65","author":"M Soltanolkotabi","year":"2019","unstructured":"Soltanolkotabi, M.: Structured signal recovery from quadratic measurements: breaking sample complexity barriers via nonconvex optimization. IEEE Trans. Inform. Theory 65(4), 2374\u20132400 (2019)","journal-title":"IEEE Trans. Inform. Theory"},{"key":"1433_CR33","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-030-31351-7_9","volume-title":"Handbook of Variational Methods for Nonlinear Geometric Data","author":"A Uschmajew","year":"2020","unstructured":"Uschmajew, A., Vandereycken, B.: Geometric methods on low-rank matrix and tensor manifolds. In: Grohs, P., Holler, M., Weinmann, A. (eds.) Handbook of Variational Methods for Nonlinear Geometric Data, pp. 261\u2013313. Springer, Cham (2020)"},{"issue":"2","key":"1433_CR34","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.1137\/110845768","volume":"23","author":"B Vandereycken","year":"2013","unstructured":"Vandereycken, B.: Low-rank matrix completion by Riemannian optimization. SIAM J. Optim. 23(2), 1214\u20131236 (2013)","journal-title":"SIAM J. Optim."},{"issue":"3","key":"1433_CR35","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.1137\/15M1050525","volume":"37","author":"K Wei","year":"2016","unstructured":"Wei, K., Cai, J.-F., Chan, T.F., Leung, S.: Guarantees of Riemannian optimization for low rank matrix recovery. SIAM J. Matrix Anal. Appl. 37(3), 1198\u20131222 (2016)","journal-title":"SIAM J. Matrix Anal. Appl."}],"container-title":["Numerical Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11075-022-01433-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11075-022-01433-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11075-022-01433-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T05:10:05Z","timestamp":1683522605000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11075-022-01433-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,29]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["1433"],"URL":"https:\/\/doi.org\/10.1007\/s11075-022-01433-5","relation":{},"ISSN":["1017-1398","1572-9265"],"issn-type":[{"value":"1017-1398","type":"print"},{"value":"1572-9265","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,29]]},"assertion":[{"value":"16 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}