Strong Convexity of Sets in Riemannian Manifolds

Abstract

Curvature properties of convex objects, such as strong convexity, are important in designing and analyzing convex optimization algorithms in the Hilbertian or Riemannian settings. In the case of the Hilbertian setting, strongly convex sets are well studied. Herein, we propose various definitions of strong convexity for uniquely geodesic sets in a Riemannian manifold. We study their relationship, propose tools to determine the geodesic strongly convex nature of sets, and analyze the convergence of optimization algorithms over those sets. In particular, we demonstrate that the Riemannian Frank-Wolfe algorithm enjoys a global linear convergence rate when the Riemannian scaling inequalities hold.

References in corpus (7)

• Sparsity, variance and curvature in multi-armed bandits
• Conditional Gradient Methods
• Local and Global Uniform Convexity Conditions
• Curvature-Dependant Global Convergence Rates for Optimization on Manifolds of Bounded Geometry
• Online learning with exponential weights in metric spaces
• The exponentially weighted average forecaster in geodesic spaces of non-positive curvature
• Accelerated Riemannian Optimization: Handling Constraints with a Prox to Bound Geometric Penalties