An optimization problem on the sphere
Machine Learning
2008-05-16 v1 Computational Geometry
Abstract
We prove existence and uniqueness of the minimizer for the average geodesic distance to the points of a geodesically convex set on the sphere. This implies a corresponding existence and uniqueness result for an optimal algorithm for halfspace learning, when data and target functions are drawn from the uniform distribution.
Cite
@article{arxiv.0805.2362,
title = {An optimization problem on the sphere},
author = {Andreas Maurer},
journal= {arXiv preprint arXiv:0805.2362},
year = {2008}
}