Exponential inequalities for dependent V-statistics via random Fourier features

• DOI: 10.48550/arxiv.2001.01297
• Publication Date: 2020-01-01
• Authors: Yandi Shen; Fang Han; Daniela Witten
• Keywords: Kernel (algebra)

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