Exponential inequalities for dependent V-statistics via random Fourier features

01/05/2020

∙

by   Yandi Shen, et al.

∙

0

∙

share

We establish exponential inequalities for a class of V-statistics under strong mixing conditions. Our theory is developed via a novel kernel expansion based on random Fourier features and the use of a probabilistic method. This type of expansion is new and useful for handling many notorious classes of kernels.