Concentration of Lipschitz Functions of Negatively Dependent Variables
Probability
2018-04-27 v1
Abstract
We explore the question whether Lipschitz functions of random variables under various forms of negative correlation satisfy concentration bounds similar to McDiarmid's inequality for independent random variables. We prove such a concentration bound for random variables satisfying the condition of negative regression, correcting an earlier proof by Dubhashi and Ranjan.
Keywords
Cite
@article{arxiv.1804.10084,
title = {Concentration of Lipschitz Functions of Negatively Dependent Variables},
author = {Kevin Garbe and Jan Vondrak},
journal= {arXiv preprint arXiv:1804.10084},
year = {2018}
}