Some Hoeffding- and Bernstein-type Concentration Inequalities
Probability
2021-06-24 v4 Machine Learning
Machine Learning
Abstract
We prove concentration inequalities for functions of independent random variables {under} sub-gaussian and sub-exponential conditions. The utility of the inequalities is demonstrated by an extension of the now classical method of Rademacher complexities to Lipschitz function classes and unbounded sub-exponential distribution.
Cite
@article{arxiv.2102.06304,
title = {Some Hoeffding- and Bernstein-type Concentration Inequalities},
author = {Andreas Maurer and Massimiliano Pontil},
journal= {arXiv preprint arXiv:2102.06304},
year = {2021}
}