English

A vector-contraction inequality for Rademacher complexities using $p$-stable variables

Probability 2021-07-27 v2 Machine Learning Machine Learning

Abstract

Andreas Maurer in the paper "A vector-contraction inequality for Rademacher complexities" extended the contraction inequality for Rademacher averages to Lipschitz functions with vector-valued domains; He did it replacing the Rademacher variables in the bounding expression by arbitrary idd symmetric and sub-gaussian variables. We will see how to extend this work when we replace sub-gaussian variables by pp-stable variables for 1<p<21<p<2.

Keywords

Cite

@article{arxiv.1912.10136,
  title  = {A vector-contraction inequality for Rademacher complexities using $p$-stable variables},
  author = {Oscar Zatarain-Vera},
  journal= {arXiv preprint arXiv:1912.10136},
  year   = {2021}
}
R2 v1 2026-06-23T12:53:06.860Z