Uniform k-step recovery with CMF dictionaries

Clément Elvira 1 Rémi Gribonval 1 Cédric Herzet 2 Charles Soussen 3
1 PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
2 SIMSMART - SIMulation pARTiculaire de Modèles Stochastiques
IRMAR - Institut de Recherche Mathématique de Rennes, Inria Rennes – Bretagne Atlantique
Abstract : 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.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-02157561
Contributor : Clément Elvira <>
Submitted on : Monday, June 17, 2019 - 10:05:04 AM
Last modification on : Friday, September 13, 2019 - 9:50:02 AM

File

spars.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02157561, version 1

Citation

Clément Elvira, Rémi Gribonval, Cédric Herzet, Charles Soussen. Uniform k-step recovery with CMF dictionaries. SPARS 2019 - Signal Processing with Adaptive Sparse Structured Representations, Jul 2019, Toulouse, France. pp.1-2. ⟨hal-02157561⟩

Share

Metrics

Record views

190

Files downloads

401