ResearchTrend.AI
2
9

Exponential inequalities for dependent V-statistics via random Fourier features

Abstract

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.

View on arXiv
Comments on this paper