On the distance between mean and geometric median in high dimensions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Schwank, Richard, Drton, Mathias
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918343863173120
author Schwank, Richard
Drton, Mathias
author_facet Schwank, Richard
Drton, Mathias
contents The geometric median, a notion of center for multivariate distributions, has gained recent attention in robust statistics and machine learning. Although conceptually distinct from the mean (i.e., expectation), we demonstrate that both are very close in high dimensions when the dependence between the distribution components is suitably controlled. Concretely, we find an upper bound on the distance that vanishes with the dimension asymptotically, and derive a rate-matching first order expansion of the geometric median components. Simulations illustrate and confirm our results.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12926
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the distance between mean and geometric median in high dimensions
Schwank, Richard
Drton, Mathias
Statistics Theory
Probability
Machine Learning
The geometric median, a notion of center for multivariate distributions, has gained recent attention in robust statistics and machine learning. Although conceptually distinct from the mean (i.e., expectation), we demonstrate that both are very close in high dimensions when the dependence between the distribution components is suitably controlled. Concretely, we find an upper bound on the distance that vanishes with the dimension asymptotically, and derive a rate-matching first order expansion of the geometric median components. Simulations illustrate and confirm our results.
title On the distance between mean and geometric median in high dimensions
topic Statistics Theory
Probability
Machine Learning
url https://arxiv.org/abs/2508.12926