Concentration inequalities under sub-Gaussian and sub-exponential conditions

Andreas Maurer; Massimiliano Pontil

NeurIPS 2021poster38 citations

Concentration inequalities under sub-Gaussian and sub-exponential conditions

Abstract

We prove analogues of the popular bounded difference inequality (also called McDiarmid's inequality) for functions of independent random variables under sub-gaussian and sub-exponential conditions. Applied to vector-valued concentration and the method of Rademacher complexities these inequalities allow an easy extension of uniform convergence results for PCA and linear regression to the case potentially unbounded input- and output variables.

Statistical Learning TheoryConcentration Inequalities

BibTeX

@inproceedings{
maurer2021concentration,
title={Concentration inequalities under sub-Gaussian and sub-exponential conditions},
author={Andreas Maurer and Massimiliano Pontil},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=WJPAqX5M-2}
}