Empirical bounds for functions with weak interactions
Machine Learning
2018-03-13 v1
Abstract
We provide sharp empirical estimates of expectation, variance and normal approximation for a class of statistics whose variation in any argument does not change too much when another argument is modified. Examples of such weak interactions are furnished by U- and V-statistics, Lipschitz L-statistics and various error functionals of L2-regularized algorithms and Gibbs algorithms.
Keywords
Cite
@article{arxiv.1803.03934,
title = {Empirical bounds for functions with weak interactions},
author = {Andreas Maurer and Massimiliano Pontil},
journal= {arXiv preprint arXiv:1803.03934},
year = {2018}
}