Exponential inequalities for dependent V-statistics via random Fourier features

2020/01/05 by Yandi Shen, Fang Han, Shen, Yandi +3
Engineering · Mathematics · #Control Systems and Identification #FOS: Mathematics #Markov Chains and Monte Carlo Methods #Probability (math.PR) #Statistical Methods and Inference #Statistics Theory (math.ST)

paper · pdf · doi:10.48550/arxiv.2001.01297

openalex publication_date 2020/01/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Tail behavior of dependent V-statistics and its applications
• Exponential inequalities for the distribution tails of canonical U- and V-statistics of ρ-mixing observations
• An Exponential Inequality for U-Statistics under Mixing Conditions
• An exponential inequality for Hilbert-valued U-statistics of i.i.d. data
• V-statistics and Variance Estimation