Show simple item record

Sparse Regularization on Thin Grids I: the LASSO

dc.contributor.authorDuval, Vincent
HAL ID: 7243
ORCID: 0000-0002-7709-256X
dc.contributor.authorPeyré, Gabriel
HAL ID: 1211
dc.date.accessioned2018-03-01T10:13:06Z
dc.date.available2018-03-01T10:13:06Z
dc.date.issued2017
dc.identifier.issn0266-5611
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/17490
dc.language.isoenen
dc.subjectCompressed sensing
dc.subjectDeconvolution
dc.subjectSparse Approximation
dc.subjectInverse problems
dc.subjectBasis pursuit
dc.subject.ddc621.3en
dc.titleSparse Regularization on Thin Grids I: the LASSO
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenThis article analyzes the recovery performance in the presence of noise of sparse L1 regularization, which is often referred to as the Lasso or Basis-Pursuit. We study the behavior of the method for inverse problems regularization when the discretization step size tends to zero. We assume that the sought after sparse sum of Diracs is recovered when there is no noise (a condition which has been thoroughly studied in the literature) and we study what is the support (in particular the number of Dirac masses) estimated by the Lasso when noise is added to the observation. We identify a precise non-degeneracy condition that guarantees that the recovered support is close to the initial one. More precisely, we show that, in the small noise regime, when the non-degeneracy condition holds, this method estimates twice the number of spikes as the number of original spikes. Indeed, we prove that the Lasso detects two neighboring spikes around each location of an original spike. While this paper is focussed on cases where the observations vary smoothly with the spikes locations (e.g. the deconvolution problem with a smooth kernel), an interesting by-product is an abstract analysis of the support stability of discrete L1 regularization, which is of an independent interest. We illustrate the usefulness of this abstract analysis to analyze for the first time the support instability of compressed sensing recovery.
dc.relation.isversionofjnlnameInverse Problems
dc.relation.isversionofjnlvol33
dc.relation.isversionofjnlissue5
dc.relation.isversionofjnldate2017
dc.relation.isversionofdoi10.1088/1361-6420/aa5e12
dc.relation.isversionofjnlpublisherIOP Science
dc.subject.ddclabelTraitement du signalen
dc.relation.forthcomingnonen
dc.relation.forthcomingprintnonen
dc.description.ssrncandidatenon
dc.description.halcandidatenon
dc.description.readershiprecherche
dc.description.audienceInternational
dc.relation.Isversionofjnlpeerreviewedoui
dc.date.updated2018-04-13T09:17:02Z


Files in this item

Thumbnail
Name:
Asymptotic-Lasso.pdf
Size:
516.8Kb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record