Finite sample bounds for barycenter estimation in geodesic spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brunel, Victor-Emmanuel, Serres, Jordan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909505291288576
author Brunel, Victor-Emmanuel
Serres, Jordan
author_facet Brunel, Victor-Emmanuel
Serres, Jordan
contents We study the problem of estimating the barycenter of a distribution given i.i.d. data in a geodesic space. Assuming an upper curvature bound in Alexandrov's sense and a support condition ensuring the strong geodesic convexity of the barycenter problem, we establish finite-sample error bounds in expectation and with high probability. Our results generalize Hoeffding- and Bernstein-type concentration inequalities from Euclidean to geodesic spaces. Building on these concentration inequalities, we derive statistical guarantees for two efficient algorithms for the computation of barycenters.
format Preprint
id arxiv_https___arxiv_org_abs_2502_14069
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finite sample bounds for barycenter estimation in geodesic spaces
Brunel, Victor-Emmanuel
Serres, Jordan
Statistics Theory
Probability
Machine Learning
We study the problem of estimating the barycenter of a distribution given i.i.d. data in a geodesic space. Assuming an upper curvature bound in Alexandrov's sense and a support condition ensuring the strong geodesic convexity of the barycenter problem, we establish finite-sample error bounds in expectation and with high probability. Our results generalize Hoeffding- and Bernstein-type concentration inequalities from Euclidean to geodesic spaces. Building on these concentration inequalities, we derive statistical guarantees for two efficient algorithms for the computation of barycenters.
title Finite sample bounds for barycenter estimation in geodesic spaces
topic Statistics Theory
Probability
Machine Learning
url https://arxiv.org/abs/2502.14069