On the distance between mean and geometric median in high dimensions
Statistics Theory
2026-02-19 v3 Probability
Machine Learning
Statistics Theory
Abstract
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.
Cite
@article{arxiv.2508.12926,
title = {On the distance between mean and geometric median in high dimensions},
author = {Richard Schwank and Mathias Drton},
journal= {arXiv preprint arXiv:2508.12926},
year = {2026}
}
Comments
Background section added and proofs shortened