Early stopping and polynomial smoothing in regression with reproducing kernels

Abstract

In this paper, we study the problem of early stopping for iterative learning algorithms in a reproducing kernel Hilbert space (RKHS) in the nonparametric regression framework. In particular, we work with the gradient descent and (iterative) kernel ridge regression algorithms. We present a data-driven rule to perform early stopping without a validation set that is based on the so-called minimum discrepancy principle. This method enjoys only one assumption on the regression function: it belongs to a reproducing kernel Hilbert space (RKHS). The proposed rule is proved to be minimax-optimal over different types of kernel spaces, including finite-rank and Sobolev smoothness classes. The proof is derived from the fixed-point analysis of the localized Rademacher complexities, which is a standard technique for obtaining optimal rates in the nonparametric regression literature. In addition to that, we present simulation results on artificial datasets that show the comparable performance of the designed rule with respect to other stopping rules such as the one determined by V-fold cross-validation.

A shortened version of the article

References in corpus (6)

• Benign Overfitting in Linear Regression
• 2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization
• Early stopping and non-parametric regression: An optimal data-dependent stopping rule
• Convergence rates of Kernel Conjugate Gradient for random design regression
• A Continuous-Time View of Early Stopping for Least Squares
• Analyzing the discrepancy principle for kernelized spectral filter learning algorithms