Fast off-the-grid sparse recovery with over-parametrized projected gradient descent
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | BÉNARD, Pierre-Jean | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | TRAONMILIN, Yann | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | AUJOL, Jean-François | |
| dc.date.accessioned | 2024-04-04T02:40:44Z | |
| dc.date.available | 2024-04-04T02:40:44Z | |
| dc.date.conference | 2022 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/191088 | |
| dc.description.abstractEn | We consider the problem of recovering off-the-grid spikes from Fourier measurements. Successful methods such as sliding Frank-Wolfe and continuous orthogonal matching pursuit (OMP) iteratively add spikes to the solution then perform a costly (when the number of spikes is large) descent on all parameters at each iteration. In 2D, it was shown that performing a projected gradient descent (PGD) from a gridded over-parametrized initialization was faster than continuous orthogonal matching pursuit. In this paper, we propose an off-the-grid over-parametrized initialization of the PGD based on OMP that permits to fully avoid grids and gives faster results in 3D. | |
| dc.description.sponsorship | Régularisation performante de problèmes inverses en grande dimension pour le traitement de données - ANR-20-CE40-0001 | |
| dc.language.iso | en | |
| dc.subject.en | spike super-resolution | |
| dc.subject.en | non-convex optimization | |
| dc.subject.en | over-parametrization | |
| dc.subject.en | projected gradient descent | |
| dc.subject.en | continuous orthogonal matching pursuit | |
| dc.title.en | Fast off-the-grid sparse recovery with over-parametrized projected gradient descent | |
| dc.type | Communication dans un congrès | |
| dc.subject.hal | Mathématiques [math]/Optimisation et contrôle [math.OC] | |
| dc.subject.hal | Informatique [cs]/Traitement du signal et de l'image | |
| dc.identifier.arxiv | 2202.13757 | |
| 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 | 2022 30th European Signal Processing Conference (EUSIPCO) | |
| bordeaux.country | FR | |
| bordeaux.conference.city | Belgrade (Serbia) | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-03590939 | |
| hal.version | 1 | |
| hal.proceedings | non | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-03590939v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=B%C3%89NARD,%20Pierre-Jean&TRAONMILIN,%20Yann&AUJOL,%20Jean-Fran%C3%A7ois&rft.genre=unknown |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||