A Riemannian Corollary of Helly's Theorem

04/28/2018
by   Alexander Rusciano, et al.
0

We introduce a notion of halfspace for Hadamard manifolds that is natural in the context of convex optimization. For this notion of halfspace, we generalize a classic result of Grünbaum, which itself is a corollary of Helly's theorem. Namely, given a probability distribution on the manifold, there is a point for which all halfspaces based at this point have at least 1/n+1 of the mass. As an application, the gradient oracle complexity of convex optimization is polynomial in the parameters defining the problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/24/2019

Sampling and Optimization on Convex Sets in Riemannian Manifolds of Non-Negative Curvature

The Euclidean space notion of convex sets (and functions) generalizes to...
research
02/19/2016

First-order Methods for Geodesically Convex Optimization

Geodesic convexity generalizes the notion of (vector space) convexity to...
research
08/06/2019

Fenchel Duality for Convex Optimization and a Primal Dual Algorithm on Riemannian Manifolds

This paper introduces a new duality theory that generalizes the classica...
research
07/24/2023

Open Problem: Polynomial linearly-convergent method for geodesically convex optimization?

Let f ℳ→ℝ be a Lipschitz and geodesically convex function defined on a d...
research
06/03/2021

Convex optimization

This textbook is based on lectures given by the authors at MIPT (Moscow)...
research
11/25/2021

Negative curvature obstructs acceleration for geodesically convex optimization, even with exact first-order oracles

Hamilton and Moitra (2021) showed that, in certain regimes, it is not po...
research
10/27/2019

Towards a theory of non-commutative optimization: geodesic first and second order methods for moment maps and polytopes

This paper initiates a systematic development of a theory of non-commuta...

Please sign up or login with your details

Forgot password? Click here to reset