Optimization Online


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

Jingwei Liang(jingwei.liang***at***ensicaen.fr)
Jalal Fadili(Jalal.Fadili***at***ensicaen.fr)
Gabriel Peyre(Gabriel.Peyre***at***ceremade.dauphine.fr)

Abstract: 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-Lojasiewicz 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.

Keywords: Non-convex optimization, inertial Forward--Backward, Kurdyka-Lojasiewicz, Partial smoothness, Local linear convergence

Category 1: Convex and Nonsmooth Optimization (Nonsmooth Optimization )


Download: [PDF]

Entry Submitted: 06/06/2016
Entry Accepted: 06/06/2016
Entry Last Modified: 06/06/2016

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society