Recovery and convergence rate of the Frank-Wolfe Algorithm for the m-EXACT-SPARSE Problem - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Information Theory Année : 2019

Recovery and convergence rate of the Frank-Wolfe Algorithm for the m-EXACT-SPARSE Problem

Résumé

We study the properties of the Frank-Wolfe algorithm to solve the m-EXACT-SPARSE reconstruction problem, where a signal y must be expressed as a sparse linear combination of a predefined set of atoms, called dictionary. We prove that when the signal is sparse enough with respect to the coherence of the dictionary, then the iterative process implemented by the Frank-Wolfe algorithm only recruits atoms from the support of the signal, that is the smallest set of atoms from the dictionary that allows for a perfect reconstruction of y. We also prove that under this same condition, there exists an iteration beyond which the algorithm converges exponentially.
Fichier principal
Vignette du fichier
Franck_Wolfe_Cherfaoui_and_al_TIT.pdf (335.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01919761 , version 1 (12-11-2018)
hal-01919761 , version 2 (17-05-2019)

Identifiants

  • HAL Id : hal-01919761 , version 2

Citer

Farah Cherfaoui, Valentin Emiya, Liva Ralaivola, Sandrine Anthoine. Recovery and convergence rate of the Frank-Wolfe Algorithm for the m-EXACT-SPARSE Problem. IEEE Transactions on Information Theory, 2019, 65 (11). ⟨hal-01919761v2⟩
293 Consultations
368 Téléchargements

Partager

Gmail Facebook X LinkedIn More