An Upper Bound of the Bias of Nadaraya-Watson Kernel Regression under Lipschitz Assumptions

01/29/2020

∙

The Nadaraya-Watson kernel estimator is among the most popular nonparameteric regression technique thanks to its simplicity. Its asymptotic bias has been studied by Rosenblatt in 1969 and has been reported in a number of related literature. However, Rosenblatt's analysis is only valid for infinitesimal bandwidth. In contrast, we propose in this paper an upper bound of the bias which holds for finite bandwidths. Moreover, contrarily to the classic analysis we allow for discontinuous first order derivative of the regression function, we extend our bounds for multidimensional domains and we include the knowledge of the bound of the regression function when it exists and if it is known, to obtain a tighter bound. We believe that this work has potential applications in those fields where some hard guarantees on the error are needed

READ FULL TEXT

An Upper Bound of the Bias of Nadaraya-Watson Kernel Regression under Lipschitz Assumptions

Variable bandwidth kernel regression estimation

Rederiving the Upper Bound for Halving Edges using Cardano's Formula

Improvements of Polya Upper Bound for Cumulative Standard Normal Distribution and Related Functions

Simple and Almost Assumption-Free Out-of-Sample Bound for Random Feature Mapping

On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions

Supplementary Material for CDC Submission: On Influence of Ill-conditioned Regression Matrix on Hyper-parameter Estimators for Kernel-based Regularization Methods

A priori guarantees of finite-time convergence for Deep Neural Networks

An Upper Bound of the Bias of Nadaraya-Watson Kernel Regression under Lipschitz Assumptions

Related Research

Variable bandwidth kernel regression estimation

Rederiving the Upper Bound for Halving Edges using Cardano's Formula

Improvements of Polya Upper Bound for Cumulative Standard Normal Distribution and Related Functions

Simple and Almost Assumption-Free Out-of-Sample Bound for Random Feature Mapping

On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions

Supplementary Material for CDC Submission: On Influence of Ill-conditioned Regression Matrix on Hyper-parameter Estimators for Kernel-based Regularization Methods

A priori guarantees of finite-time convergence for Deep Neural Networks