Convergence of inexact descent methods for nonconvex optimization on Riemannian manifolds

Details Convergence of inexact descent methods for nonconvex optimization on Riemannian manifolds Convergence of inexact descent methods for nonconvex optimization on Riemannian manifolds

2011-03-24

arxiv.org/abs/1103.4828v1

Mathematics

Numerical Analysis

28 pages

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Convergence of inexact descent methods for nonconvex optimization on Riemannian manifolds does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Convergence of inexact descent methods for nonconvex optimization on Riemannian manifolds, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Convergence of inexact descent methods for nonconvex optimization on Riemannian manifolds will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-48910