{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T20:23:03Z","timestamp":1787343783570,"version":"build-2736575974"},"reference-count":39,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"2","funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-18-CE40-0005"],"award-info":[{"award-number":["ANR-18-CE40-0005"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ANER RAGA","award":["G048CVCRB-2018ZZ"],"award-info":[{"award-number":["G048CVCRB-2018ZZ"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Optim."],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>Analysis sparsity is a common prior in inverse problem or machine learning including special cases such as total variation regularization, edge Lasso, and fused Lasso. We study the geometry of the solution set (a polyhedron) of the analysis [Formula: see text] regularization (with [Formula: see text] data fidelity term) when it is not reduced to a singleton without any assumption of the analysis dictionary nor the degradation operator. In contrast with most theoretical work, we do not focus on giving uniqueness and\/or stability results but rather describe a worst-case scenario where the solution set can be big in terms of dimension. Leveraging a fine analysis of the sublevel set of the regularizer itself, we draw a connection between support of a solution and the minimal face containing it and, in particular, prove that extreme points can be recovered thanks to an algebraic test. Moreover, we draw a connection between the sign pattern of a solution and the ambient dimension of the smallest face containing it. Finally, we show that any arbitrary subpolyhedra of the level set can be seen as a solution set of sparse analysis regularization with explicit parameters.<\/jats:p>","DOI":"10.1137\/19m1271877","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T10:08:16Z","timestamp":1687255696000},"page":"842-867","source":"Crossref","is-referenced-by-count":2,"title":["The Geometry of Sparse Analysis Regularization"],"prefix":"10.1137","volume":"33","author":[{"given":"Xavier","family":"Dupuis","sequence":"first","affiliation":[{"name":"Universit\u00e9 de Bourgogne, Dijon, France."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4077-708X","authenticated-orcid":true,"given":"Samuel","family":"Vaiter","sequence":"additional","affiliation":[{"name":"CNRS & Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, LJAD, Nice 06000, France."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2023,6,20]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"A. Ali  and \nR. J. Tibshirani , The Generalized Lasso Problem and Uniqueness, preprint, arXiv:1805.07682, 2018.","DOI":"10.1214\/19-EJS1569"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-018-1385-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1090\/S0273-0979-1980-14712-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511586507"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1969-0256265-X"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/18M1200750"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(91)90087-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-010-0251-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1214\/009053604000000067"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/23\/3\/007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/20-EJS1687"},{"key":"ref13","volume":"17","author":"Guyon I.","year":"2004","journal-title":"NeurIPS"},{"key":"ref14","volume-title":"Convex analysis and minimization algorithms I: Fundamentals","volume":"305","author":"Hiriart-Urruty J.-B.","year":"2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF02192142"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(71)90184-3"},{"key":"ref17","unstructured":"J. Mairal  and \nB. Yu , Complexity Analysis of the Lasso Regularization Path, preprint, arXiv:1205.0079, 2012."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/02331939908844431"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(88)90047-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1112\/S0025579300002850"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2012.03.006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1515\/9781400873173"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref24","unstructured":"U. Schneider  and \nP. Tardivel , The Geometry of Uniqueness, Sparsity and Clustering in Penalized Estimation, preprint, arXiv:2004.09106, 2020."},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"B. Sch\u00f6lkopf , \nR. Herbrich , and \nA. J. Smola , A generalized representer theorem, in International Conference on Computational Learning Theory, Springer, New York, 2001, pp. 416\u2013426.","DOI":"10.1007\/3-540-44581-1_27"},{"key":"ref26","unstructured":"J. Sharpnack , \nA. Singh , and \nA. Rinaldo , Sparsistency of the edge lasso over graphs, in Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, \nN. D. Lawrence  and \nM. Girolami , eds. Proc. Mach. Learn. Res. 22, La Palma, Canary Islands, PMLR, 2012, pp. 1028\u20131036, https:\/\/proceedings.mlr.press\/v22\/sharpnack12.html."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/10-EJS578"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/S0036142903422429"},{"key":"ref29","unstructured":"P. J. C. Tardivel , \nT. Skalski , \nP. Graczyk , and \nU. Schneider , The Geometry of Model Recovery by Penalized and Thresholded Estimators, in process, 2021, https:\/\/hal.archives-ouvertes.fr\/hal-03262087."},{"key":"ref30","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"Tibshirani R.","year":"1996","journal-title":"J. R. Stat. Soc. Ser. B (Methodol.)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00490.x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/13-EJS815"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1214\/11-AOS878"},{"key":"ref34","doi-asserted-by":"crossref","unstructured":"M. Unser , A Unifying Representer Theorem for Inverse Problems and Machine Learning, preprint, arXiv:1903.00687, 2019.","DOI":"10.1007\/s10208-020-09472-x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2012.11.006"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2233859"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10444-016-9467-y"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-8431-1"}],"container-title":["SIAM Journal on Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/19M1271877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T19:23:30Z","timestamp":1787340210000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/19M1271877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,20]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,6,30]]}},"alternative-id":["10.1137\/19M1271877"],"URL":"https:\/\/doi.org\/10.1137\/19m1271877","relation":{},"ISSN":["1052-6234","1095-7189"],"issn-type":[{"value":"1052-6234","type":"print"},{"value":"1095-7189","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,20]]}}}