Finite de Finetti bounds in relative entropy
Probability
2024-07-19 v1 Information Theory
math.IT
Abstract
We review old and recent finite de Finetti theorems in total variation distance and in relative entropy, and we highlight their connections with bounds on the difference between sampling with and without replacement. We also establish two new finite de Finetti theorems for exchangeable random vectors taking values in arbitrary spaces. These bounds are tight, and they are independent of the size and the dimension of the underlying space.
Cite
@article{arxiv.2407.12921,
title = {Finite de Finetti bounds in relative entropy},
author = {Lampros Gavalakis and Oliver Johnson and Ioannis Kontoyiannis},
journal= {arXiv preprint arXiv:2407.12921},
year = {2024}
}
Comments
18 pages, no figures