Uniform concentration and symmetrization for weak interactions

[edit]

Andreas Maurer, Massimiliano Pontil ;
Proceedings of the Thirty-Second Conference on Learning Theory, PMLR 99:2372-2387, 2019.

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.

Related Material