Exact recovery analysis of non-negative orthogonal matching pursuit - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Exact recovery analysis of non-negative orthogonal matching pursuit

Résumé

It is well-known that Orthogonal Matching Pursuit (OMP) recovers the exact support of K-sparse signals under the condition µ < 1/(2K − 1) where µ denotes the mutual coherence of the dictionary. In this communication, we show that under the same condition and if the unknown K-sparse signal is non-negative, the weights of the atoms selected by OMP are non-negative at any of the first K iterations. Therefore, the generalized version of OMP to the non-negative setting (NNOMP) identifies with OMP, which allows us to establish an exact recovery analysis of NNOMP under the mutual coherence condition.
Fichier principal
Vignette du fichier
nguyen.pdf (134.02 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02378709 , version 1 (25-11-2019)

Identifiants

  • HAL Id : hal-02378709 , version 1

Citer

Thi Thanh Nguyen, Charles Soussen, Jérôme Idier, El-Hadi Djermoune. Exact recovery analysis of non-negative orthogonal matching pursuit. Signal Processing with Adaptive Sparse Structured Representations Workshop, SPARS 2019, Jul 2019, Toulouse, France. ⟨hal-02378709⟩
179 Consultations
55 Téléchargements

Partager

Gmail Facebook X LinkedIn More