Exponential inequalities for dependent V-statistics via random Fourier features
Statistics Theory
2020-01-07 v1 Probability
Statistics Theory
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.
Cite
@article{arxiv.2001.01297,
title = {Exponential inequalities for dependent V-statistics via random Fourier features},
author = {Yandi Shen and Fang Han and Daniela Witten},
journal= {arXiv preprint arXiv:2001.01297},
year = {2020}
}
Comments
This is the first part of the arxiv preprint (arXiv:1902.02761), and is to appear in Electronic Journal of Probability (EJP). The second part of the arxiv preprint will be submitted to a statistical journal