Empirical bounds for functions with weak interactions

03/11/2018

∙

by   Andreas Maurer, et al.

∙

0

∙

share

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.