A Constant Step Stochastic Douglas-Rachford Algorithm with Application to Non Separable Regularizations - Equipe Signal, Statistique et Apprentissage Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

A Constant Step Stochastic Douglas-Rachford Algorithm with Application to Non Separable Regularizations

Résumé

The Douglas Rachford algorithm is an algorithm that converges to a minimizer of a sum of two convex functions. The algorithm consists in fixed point iterations involving computations of the proximity operators of the two functions separately. The paper investigates a stochastic version of the algorithm where both functions are random and the step size is constant. We establish that the iterates of the algorithm stay close to the set of solution with high probability when the step size is small enough. Application to structured regularization is considered.
Fichier principal
Vignette du fichier
icassp18.pdf (284.84 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02369904 , version 1 (19-11-2019)

Identifiants

Citer

Adil Salim, Pascal Bianchi, Walid Hachem. A Constant Step Stochastic Douglas-Rachford Algorithm with Application to Non Separable Regularizations. ICASSP 2018, Apr 2018, Calgary, Canada. pp.2886-2890, ⟨10.1109/ICASSP.2018.8461469⟩. ⟨hal-02369904⟩
59 Consultations
67 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More