Score: 0

On the distance between mean and geometric median in high dimensions

Published: August 18, 2025 | arXiv ID: 2508.12926v1

By: Richard Schwank, Mathias Drton

Potential Business Impact:

Makes computer guesses more accurate with more data.

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.

Country of Origin
🇩🇪 Germany

Page Count
23 pages

Category
Mathematics:
Statistics Theory