A Multi-step Inertial Forward–Backward Splitting Method for Non-convex Optimization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

A Multi-step Inertial Forward–Backward Splitting Method for Non-convex Optimization

Résumé

In this paper, we propose a multi-step inertial Forward–Backward splitting algorithm for minimizing the sum of two non-necessarily convex functions, one of which is proper lower semi-continuous while the other is differentiable with a Lipschitz continuous gradient. We first prove global convergence of the scheme with the help of the Kurdyka–Łojasiewicz property. Then, when the non-smooth part is also partly smooth relative to a smooth submanifold, we establish finite identification of the latter and provide sharp local linear convergence analysis. The proposed method is illustrated on a few problems arising from statistics and machine learning.
Fichier principal
Vignette du fichier
ncvx-mifb.pdf (762.23 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01658854 , version 1 (07-12-2017)

Identifiants

  • HAL Id : hal-01658854 , version 1

Citer

Jingwei Liang, Jalal M. Fadili, Gabriel Peyré. A Multi-step Inertial Forward–Backward Splitting Method for Non-convex Optimization. Advances in Neural Information Processing Systems (NIPS), Dec 2017, Barcelona, Spain. ⟨hal-01658854⟩
255 Consultations
64 Téléchargements

Partager

Gmail Facebook X LinkedIn More