Exact rate of convergence of the mean Wasserstein distance between the empirical and true Gaussian distribution

preprint2020arXivOpen access

Abstract

We study the Wasserstein distance W2W_2 for Gaussian samples. We establish the exact rate of convergence log⁡log⁡n/n\sqrt{\log\log n/n} of the expected value of the W2W_2 distance between the empirical and true c.d.f.c.d.f.'s for the normal distribution. We also show that the rate of weak convergence is unexpectedly 1/n1/\sqrt{n} in the case of two correlated Gaussian samples.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.