Theoretical Analysis of Domain Adaptation with Optimal Transport

TL;DR

This paper explores how optimal transportation theory, especially the Wasserstein metric, can enhance the theoretical understanding and guarantees of domain adaptation across various learning scenarios.

Contribution

It introduces a theoretical framework using optimal transport for domain adaptation, providing generalization guarantees and insights into its advantages over existing methods.

Findings

Wasserstein metric offers a promising divergence measure for DA

Theoretical guarantees are established for multiple DA settings

Insights into when optimal transport-based analysis outperforms other frameworks

Abstract

Domain adaptation (DA) is an important and emerging field of machine learning that tackles the problem occurring when the distributions of training (source domain) and test (target domain) data are similar but different. Current theoretical results show that the efficiency of DA algorithms depends on their capacity of minimizing the divergence between source and target probability distributions. In this paper, we provide a theoretical study on the advantages that concepts borrowed from optimal transportation theory can bring to DA. In particular, we show that the Wasserstein metric can be used as a divergence measure between distributions to obtain generalization guarantees for three different learning settings: (i) classic DA with unsupervised target data (ii) DA combining source and target labeled data, (iii) multiple source DA. Based on the obtained results, we provide some insights showing when this analysis can be tighter than other existing frameworks.