OMP AND CONTINUOUS DICTIONARIES: IS k-STEP RECOVERY POSSIBLE? - Centre Henri Lebesgue Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

OMP AND CONTINUOUS DICTIONARIES: IS k-STEP RECOVERY POSSIBLE?

Résumé

In this work, we present new theoretical results on sparse recovery guarantees for a greedy algorithm, orthogonal matching pursuit (OMP), in the context of continuous parametric dictionaries, i.e., made up of an infinite uncountable number of atoms. We build up a family of dictionaries for which k-step recovery is possible with OMP for 1-dimensional parameters. In higher dimension, algebraic conditions become necessary and will lead us to revisit some well-known k-step discrete analyses. Finally, a toy-example illustrates the level of tightness of our sufficient conditions.
Fichier principal
Vignette du fichier
icassp.pdf (269.44 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02049486 , version 1 (26-02-2019)
hal-02049486 , version 2 (06-03-2019)
hal-02049486 , version 3 (23-04-2019)

Identifiants

Citer

Clément Elvira, Rémi Gribonval, Charles Soussen, Cédric Herzet. OMP AND CONTINUOUS DICTIONARIES: IS k-STEP RECOVERY POSSIBLE?. ICASSP 2019 - IEEE 44th International Conference on Acoustics, Speech, and Signal Processing, IEEE, May 2019, Brighton, United Kingdom. ⟨10.1109/ICASSP.2019.8683617⟩. ⟨hal-02049486v2⟩
309 Consultations
521 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More