Barycenters and a law of large numbers in Gromov hyperbolic spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Ohta, Shin-ichi
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917695530729472
author Ohta, Shin-ichi
author_facet Ohta, Shin-ichi
contents We investigate barycenters of probability measures on Gromov hyperbolic spaces, toward development of convex optimization in this class of metric spaces. We establish a contraction property (the Wasserstein distance between probability measures provides an upper bound of the distance between their barycenters), a deterministic approximation of barycenters of uniform distributions on finite points, and a kind of law of large numbers. These generalize the corresponding results on CAT(0)-spaces, up to additional terms depending on the hyperbolicity constant.
format Preprint
id arxiv_https___arxiv_org_abs_2211_00193
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Barycenters and a law of large numbers in Gromov hyperbolic spaces
Ohta, Shin-ichi
Metric Geometry
Optimization and Control
Probability
We investigate barycenters of probability measures on Gromov hyperbolic spaces, toward development of convex optimization in this class of metric spaces. We establish a contraction property (the Wasserstein distance between probability measures provides an upper bound of the distance between their barycenters), a deterministic approximation of barycenters of uniform distributions on finite points, and a kind of law of large numbers. These generalize the corresponding results on CAT(0)-spaces, up to additional terms depending on the hyperbolicity constant.
title Barycenters and a law of large numbers in Gromov hyperbolic spaces
topic Metric Geometry
Optimization and Control
Probability
url https://arxiv.org/abs/2211.00193