Thresholding gradient methods in Hilbert spaces: support identification and linear convergence - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue ESAIM: Control, Optimisation and Calculus of Variations Année : 2019

Thresholding gradient methods in Hilbert spaces: support identification and linear convergence

Lorenzo Rosasco
  • Fonction : Auteur
Silvia Villa
  • Fonction : Auteur

Résumé

We study the ℓ 1 regularized least squares optimization problem in a separable Hilbert space. We show that the iterative soft-thresholding algorithm (ISTA) converges linearly, without making any assumption on the linear operator into play or on the problem. The result is obtained combining two key concepts: the notion of extended support , a finite set containing the support, and the notion of conditioning over finite-dimensional sets . We prove that ISTA identifies the solution extended support after a finite number of iterations, and we derive linear convergence from the conditioning property, which is always satisfied for ℓ 1 regularized least squares problems. Our analysis extends to the entire class of thresholding gradient algorithms, for which we provide a conceptually new proof of strong convergence, as well as convergence rates.
Fichier principal
Vignette du fichier
1712.00357.pdf (420.22 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03886153 , version 1 (06-12-2022)

Identifiants

Citer

Guillaume Garrigos, Lorenzo Rosasco, Silvia Villa. Thresholding gradient methods in Hilbert spaces: support identification and linear convergence. ESAIM: Control, Optimisation and Calculus of Variations, 2019, 26, ⟨10.1051/cocv/2019011⟩. ⟨hal-03886153⟩
9 Consultations
17 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More