Convergence rate of inertial Forward-Backward algorithm beyond Nesterov's rule
Langue
en
Article de revue
Ce document a été publié dans
Mathematical Programming, Series A. 2018-11-12p. 1–20
Springer
Résumé en anglais
In this paper we study the convergence of an Inertial Forward-Backward algorithm, with a particular choice of an over-relaxation term. In particular we show that for a sequence of overrrelaxation parameters, that do not ...Lire la suite >
In this paper we study the convergence of an Inertial Forward-Backward algorithm, with a particular choice of an over-relaxation term. In particular we show that for a sequence of overrrelaxation parameters, that do not satisfy Nesterov’s rule one can still expect some relatively fast convergence properties for the objective function. In addition we complement this work by studying the convergence of the algorithm in the case where the proximal operator is inexactly computed with the presence of some errors and we give sufficient conditions over these errors in order to obtain some convergence properties for the objective function .< Réduire
Mots clés en anglais
Convex optimization
proximal operator
inertial FB algorithm
Nesterov’s rule
rate of convergence
Project ANR
Generalized Optimal Transport Models for Image processing - ANR-16-CE33-0010
Origine
Importé de halUnités de recherche