Convergence of inexact descent methods for nonconvex optimization on Riemannian manifolds

Abstract

In this paper we present an abstract convergence analysis of inexact descent methods in Riemannian context for functions satisfying Kurdyka-Lojasiewicz inequality. In particular, without any restrictive assumption about the sign of the sectional curvature of the manifold, we obtain full convergence of a bounded sequence generated by the proximal point method, in the case that the objective function is nonsmooth and nonconvex, and the subproblems are determined by a quasi distance which does not necessarily coincide with the Riemannian distance. Moreover, if the objective function is $C^1$ with $L$-Lipschitz gradient, not necessarily convex, but satisfying Kurdyka-Lojasiewicz inequality, full convergence of a bounded sequence generated by the steepest descent method is obtained.

arXiv comment28 pages

Cited by in corpus (5)

• Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold
• An Inexact Semi-smooth Newton Method on Riemannian Manifolds with Application to Duality-based Total Variation Denoising
• A Brief Introduction to Manifold Optimization
• An inexact augmented Lagrangian method for nonsmooth optimization on Riemannian manifold
• An Inexact Riemannian Proximal Gradient Method