On generalization in moment-based domain adaptation

Authors Werner Zellinger
Bernhard A. Moser
Susanne Saminger-Platz
Title On generalization in moment-based domain adaptation
Type article
Journal Annals of Mathematics and Artificial Intelligence
Volume online first
DOI 10.1007/s10472-020-09719-x
Month November
Year 2020
SCCH ID# 19094

Domain adaptation algorithms are designed to minimize the misclassification risk of a discriminative model for a target domain with little training data by adapting a model from a source domain with a large amount of training data. Standard approaches measure the adaptation discrepancy based on distance measures between the empirical probability distributions in the source and target domain. In this setting, we address the problem of deriving generalization bounds under practice-oriented general conditions on the underlying probability distributions. As a result, we obtain generalization bounds for domain adaptation based on finitely many moments and smoothness conditions.