Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift

Author name not available (Why is that?)

Publication date: 20 February 2023

Abstract: We develop and analyze a principled approach to kernel ridge regression under covariate shift. The goal is to learn a regression function with small mean squared error over a target distribution, based on unlabeled data from there and labeled data that may have a different feature distribution. We propose to split the labeled data into two subsets and conduct kernel ridge regression on them separately to obtain a collection of candidate models and an imputation model. We use the latter to fill the missing labels and then select the best candidate model accordingly. Our non-asymptotic excess risk bounds show that in quite general scenarios, our estimator adapts to the structure of the target distribution as well as the covariate shift. It achieves the minimax optimal error rate up to a logarithmic factor. The use of pseudo-labels in model selection does not have major negative impacts.

Has companion code repository: https://github.com/kw2934/krr

Mathematics Subject Classification ID

No records found.

This page was built for publication: Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6427086)