General regularization in covariate shift adaptation

Sample reweighting is one of the most widely used methods for correcting the error of least squares learning algorithms in reproducing kernel Hilbert spaces (RKHS), that is caused by future data distributions that are different from the training data distribution. In practical situations, the sample...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-07
Main Authors: Nguyen, Duc Hoan, Pereverzyev, Sergei V, Zellinger, Werner
Format: Article
Language:English
Subjects:
Algorithms
Error correction
Hilbert space
Kernels
Machine learning
Regularization
Smoothness
Supervised learning
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sample reweighting is one of the most widely used methods for correcting the error of least squares learning algorithms in reproducing kernel Hilbert spaces (RKHS), that is caused by future data distributions that are different from the training data distribution. In practical situations, the sample weights are determined by values of the estimated Radon-Nikodým derivative, of the future data distribution w.r.t.~the training data distribution. In this work, we review known error bounds for reweighted kernel regression in RKHS and obtain, by combination, novel results. We show under weak smoothness conditions, that the amount of samples, needed to achieve the same order of accuracy as in the standard supervised learning without differences in data distributions, is smaller than proven by state-of-the-art analyses.
ISSN:2331-8422