Statistically and Computationally Efficient Variance Estimator for Kernel Ridge Regression

09/17/2018

∙

by Meimei Liu, et al.

∙

Duke University

∙

Purdue University

∙

In this paper, we propose a random projection approach to estimate variance in kernel ridge regression. Our approach leads to a consistent estimator of the true variance, while being computationally more efficient. Our variance estimator is optimal for a large family of kernels, including cubic splines and Gaussian kernels. Simulation analysis is conducted to support our theory.

READ FULL TEXT

Statistically and Computationally Efficient Variance Estimator for Kernel Ridge Regression

Statistical Inference after Kernel Ridge Regression Imputation under item nonresponse

A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning

Kernel Alignment Risk Estimator: Risk Prediction from Training Data

Extrinsic Kernel Ridge Regression Classifier for Planar Kendall Shape Space

Variance estimation in pseudo-expected estimating equations for missing data

Nonparametric Testing under Random Projection

Risk Convergence of Centered Kernel Ridge Regression with Large Dimensional Data

Statistically and Computationally Efficient Variance Estimator for Kernel Ridge Regression

Related Research

Statistical Inference after Kernel Ridge Regression Imputation under item nonresponse

A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning

Kernel Alignment Risk Estimator: Risk Prediction from Training Data

Extrinsic Kernel Ridge Regression Classifier for Planar Kendall Shape Space

Variance estimation in pseudo-expected estimating equations for missing data

Nonparametric Testing under Random Projection

Risk Convergence of Centered Kernel Ridge Regression with Large Dimensional Data