Empirical bounds for functions with weak interactions

[edit]

Andreas Maurer, Massimiliano Pontil ;
Proceedings of the 31st Conference On Learning Theory, PMLR 75:987-1010, 2018.

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 $\ell_2$-regularized algorithms and Gibbs algorithms.

Related Material