Uniform concentration and symmetrization for weak interactions
Statistics Theory
2019-05-13 v4 Machine Learning
Machine Learning
Statistics Theory
Abstract
The method to derive uniform bounds with Gaussian and Rademacher complexities is extended to the case where the sample average is replaced by a nonlinear statistic. Tight bounds are obtained for U-statistics, smoothened L-statistics and error functionals of l2-regularized algorithms.
Cite
@article{arxiv.1902.01911,
title = {Uniform concentration and symmetrization for weak interactions},
author = {Andreas Maurer and Massimiliano Pontil},
journal= {arXiv preprint arXiv:1902.01911},
year = {2019}
}