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

Part of Advances in Neural Information Processing Systems 29 (NIPS 2016)

Bibtex Metadata Paper Reviews Supplemental

Authors

Jingwei Liang, Jalal Fadili, Gabriel Peyré

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–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.