Afficher la notice abrégée

dc.contributor.authorVaiter, Samuel
dc.contributor.authorPeyré, Gabriel
dc.contributor.authorFadili, Jalal
dc.date.accessioned2017-03-18T12:07:00Z
dc.date.available2017-03-18T12:07:00Z
dc.date.issued2015
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/16393
dc.language.isoenen
dc.subjectInverse problemsen
dc.subjectregularization theoryen
dc.subject.ddc621.3en
dc.titleLow Complexity Regularization of Linear Inverse Problemsen
dc.typeChapitre d'ouvrage
dc.description.abstractenInverse problems and regularization theory is a central theme in imaging sciences, statistics, and machine learning. The goal is to reconstruct an unknown vector from partial indirect, and possibly noisy, measurements of it. A now standard method for recovering the unknown vector is to solve a convex optimization problem that enforces some prior knowledge about its structure. This chapter delivers a review of recent advances in the field where the regularization prior promotes solutions conforming to some notion of simplicity/low complexity. These priors encompass as popular examples sparsity and group sparsity (to capture the compressibility of natural signals and images), total variation and analysis sparsity (to promote piecewise regularity), and low rank (as natural extension of sparsity to matrix-valued data). Our aim is to provide a unified treatment of all these regularizations under a single umbrella, namely the theory of partial smoothness. This framework is very general and accommodates all low complexity regularizers just mentioned, as well as many others. Partial smoothness turns out to be the canonical way to encode low-dimensional models that can be linear spaces or more general smooth manifolds. This review is intended to serve as a one stop shop toward the understanding of the theoretical properties of the so-regularized solutions. It covers a large spectrum including (i) recovery guarantees and stability to noise, both in terms of ℓ 2-stability and model (manifold) identification; (ii) sensitivity analysis to perturbations of the parameters involved (in particular the observations), with applications to unbiased risk estimation; (iii) convergence properties of the forward-backward proximal splitting scheme that is particularly well suited to solve the corresponding large-scale regularized optimization problem.en
dc.identifier.citationpages103-153en
dc.relation.ispartoftitleSampling Theory, a Renaissance. Compressive Sensing and Other Developmentsen
dc.relation.ispartofeditorPfander, Götz E.
dc.relation.ispartofpublnameSpringer International Publishingen
dc.relation.ispartofpublcityBerlinen
dc.relation.ispartofdate2015
dc.relation.ispartofurl10.1007/978-3-319-19749-4en
dc.identifier.urlsitehttps://arxiv.org/abs/1407.1598v2en
dc.subject.ddclabelTraitement du signalen
dc.relation.ispartofisbn978-3-319-19748-7en
dc.relation.forthcomingnonen
dc.identifier.doi10.1007/978-3-319-19749-4_3en
dc.description.ssrncandidatenonen
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.date.updated2017-03-10T13:39:42Z
hal.person.labIds
hal.person.labIds
hal.person.labIds


Fichiers attachés à cette notice

FichiersTailleFormatConsulter

Il n'y a pas de fichiers associés à cette notice.

Ce document fait partie de la (des) collection(s) suivante(s)

Afficher la notice abrégée