Robust Sparse Analysis Regularization
| hal.structure.identifier | CEntre de REcherches en MAthématiques de la DEcision [CEREMADE] | |
| dc.contributor.author | VAITER, Samuel | |
| hal.structure.identifier | CEntre de REcherches en MAthématiques de la DEcision [CEREMADE] | |
| dc.contributor.author | PEYRÉ, Gabriel | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | DOSSAL, Charles | |
| hal.structure.identifier | Equipe Image - Laboratoire GREYC - UMR6072 | |
| dc.contributor.author | FADILI, Jalal M. | |
| dc.date.accessioned | 2024-04-04T02:24:28Z | |
| dc.date.available | 2024-04-04T02:24:28Z | |
| dc.date.created | 2011-09 | |
| dc.date.issued | 2013 | |
| dc.identifier.issn | 0018-9448 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/189818 | |
| dc.description.abstractEn | This paper investigates the theoretical guarantees of L1-analysis regularization when solving linear inverse problems. Most of previous works in the literature have mainly focused on the sparse synthesis prior where the sparsity is measured as the L1 norm of the coefficients that synthesize the signal from a given dictionary. In contrast, the more general analysis regularization minimizes the L1 norm of the correlations between the signal and the atoms in the dictionary, where these correlations define the analysis support. The corresponding variational problem encompasses several well-known regularizations such as the discrete total variation and the Fused Lasso. Our main contributions consist in deriving sufficient conditions that guarantee exact or partial analysis support recovery of the true signal in presence of noise. More precisely, we give a sufficient condition to ensure that a signal is the unique solution of the L1-analysis regularization in the noiseless case. The same condition also guarantees exact analysis support recovery and L2-robustness of the L1-analysis minimizer vis-a-vis an enough small noise in the measurements. This condition turns to be sharp for the robustness of the analysis support. To show partial support recovery and L2-robustness to an arbitrary bounded noise, we introduce a stronger sufficient condition. When specialized to the L1-synthesis regularization, our results recover some corresponding recovery and robustness guarantees previously known in the literature. From this perspective, our work is a generalization of these results. We finally illustrate these theoretical findings on several examples to study the robustness of the 1-D total variation and Fused Lasso regularizations. | |
| dc.description.sponsorship | Adaptivité pour la représentation des images naturelles et des textures - ANR-08-EMER-0009 | |
| dc.language.iso | en | |
| dc.publisher | Institute of Electrical and Electronics Engineers | |
| dc.subject.en | sparsity | |
| dc.subject.en | analysis regularization | |
| dc.subject.en | synthesis regularization | |
| dc.subject.en | inverse problems | |
| dc.subject.en | L1 minimization | |
| dc.subject.en | union of subspaces | |
| dc.subject.en | noise robustness | |
| dc.subject.en | total variation | |
| dc.subject.en | wavelets | |
| dc.subject.en | Fused Lasso | |
| dc.title.en | Robust Sparse Analysis Regularization | |
| dc.type | Article de revue | |
| dc.identifier.doi | 10.1109/TIT.2012.2233859 | |
| dc.subject.hal | Mathématiques [math]/Théorie de l'information et codage [math.IT] | |
| dc.subject.hal | Informatique [cs]/Théorie de l'information [cs.IT] | |
| dc.subject.hal | Sciences de l'ingénieur [physics]/Traitement du signal et de l'image | |
| dc.subject.hal | Informatique [cs]/Traitement du signal et de l'image | |
| dc.identifier.arxiv | 1109.6222 | |
| dc.description.sponsorshipEurope | Sparsity, Image and Geometry to Model Adaptively Visual Processings | |
| bordeaux.journal | IEEE Transactions on Information Theory | |
| bordeaux.page | 2001-2016 | |
| bordeaux.volume | 59 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.issue | 4 | |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-00627452 | |
| hal.version | 1 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-00627452v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=IEEE%20Transactions%20on%20Information%20Theory&rft.date=2013&rft.volume=59&rft.issue=4&rft.spage=2001-2016&rft.epage=2001-2016&rft.eissn=0018-9448&rft.issn=0018-9448&rft.au=VAITER,%20Samuel&PEYR%C3%89,%20Gabriel&DOSSAL,%20Charles&FADILI,%20Jalal%20M.&rft.genre=article |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||