On the Equivalence of Statistical Distances for Isotropic Convex Measures
Probability
2021-12-17 v1
Abstract
We establish quantitative comparisons between classical distances for probability distributions belonging to the class of convex probability measures. Distances include total variation distance, Wasserstein distance, Kullback-Leibler distance and more general R\'enyi divergences. This extends a result of Meckes and Meckes (2014).
Keywords
Cite
@article{arxiv.2112.09009,
title = {On the Equivalence of Statistical Distances for Isotropic Convex Measures},
author = {Arnaud Marsiglietti and Puja Pandey},
journal= {arXiv preprint arXiv:2112.09009},
year = {2021}
}
Comments
20 pages