Is the 1-norm the best convex sparse regularization?
| hal.structure.identifier | Centre National de la Recherche Scientifique [CNRS] | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | TRAONMILIN, Yann | |
| hal.structure.identifier | Centre National de la Recherche Scientifique [CNRS] | |
| hal.structure.identifier | Institut de Mathématiques de Bourgogne [Dijon] [IMB] | |
| dc.contributor.author | VAITER, Samuel | |
| hal.structure.identifier | Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio [PANAMA] | |
| dc.contributor.author | GRIBONVAL, Rémi | |
| dc.date.accessioned | 2024-04-04T03:05:41Z | |
| dc.date.available | 2024-04-04T03:05:41Z | |
| dc.date.conference | 2018-11-21 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/193269 | |
| dc.description.abstractEn | The 1-norm is a good convex regularization for the recovery of sparse vectors from under-determined linear measurements. No other convex regularization seems to surpass its sparse recovery performance. How can this be explained? To answer this question, we define several notions of " best " (convex) regulariza-tion in the context of general low-dimensional recovery and show that indeed the 1-norm is an optimal convex sparse regularization within this framework. | |
| dc.language.iso | en | |
| dc.title.en | Is the 1-norm the best convex sparse regularization? | |
| dc.type | Communication dans un congrès | |
| dc.subject.hal | Informatique [cs]/Traitement du signal et de l'image | |
| dc.subject.hal | Informatique [cs]/Théorie de l'information [cs.IT] | |
| dc.identifier.arxiv | 1806.08690 | |
| bordeaux.page | 1-11 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.conference.title | iTWIST'18 - international Traveling Workshop on Interactions between low-complexity data models and Sensing Techniques | |
| bordeaux.country | FR | |
| bordeaux.conference.city | Marseille | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-01819219 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | non | |
| hal.conference.end | 2018-11-23 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-01819219v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.spage=1-11&rft.epage=1-11&rft.au=TRAONMILIN,%20Yann&VAITER,%20Samuel&GRIBONVAL,%20R%C3%A9mi&rft.genre=unknown |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||