Path-based incremental target level algorithm on Riemannian manifolds. (2nd April 2020)

• Record Type: Journal Article
• Authors: Zhang, Peng; Bao, Gejun
• Is Part Of: Optimization. Volume 69:Number 4(2020)
• Page Start: 799
• Page End: 819
• Publication Date: 2020-04-02
• Subjects: Path-based incremental target level algorithm -- convex programming -- Riemannian manifolds; Mathematical optimization -- Periodicals; 519.7
• DOI: 10.1080/02331934.2019.1671840
• Languages: English
• ISSNs: 0233-1934

Abstract

ABSTRACT: In this paper, we propose and analyse a path-based incremental target level algorithm for minimizing a constrained convex optimization on complete Riemannian manifolds with lower bounded sectional curvature, where the object function consists of the sum of a large number of component functions. This algorithm extends, to the context of Riemannian manifolds, an incremental subgradient method emplying a version of dynamic stepsize rule. Some convergence results and iteration-complexity bounds of the algorithm are established.