Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport

by   Mourad El Hamri, et al.

Domain adaptation arises as an important problem in statistical learning theory when the data-generating processes differ between training and test samples, respectively called source and target domains. Recent theoretical advances show that the success of domain adaptation algorithms heavily relies on their ability to minimize the divergence between the probability distributions of the source and target domains. However, minimizing this divergence cannot be done independently of the minimization of other key ingredients such as the source risk or the combined error of the ideal joint hypothesis. The trade-off between these terms is often ensured by algorithmic solutions that remain implicit and not directly reflected by the theoretical guarantees. To get to the bottom of this issue, we propose in this paper a new theoretical framework for domain adaptation through hierarchical optimal transport. This framework provides more explicit generalization bounds and allows us to consider the natural hierarchical organization of samples in both domains into classes or clusters. Additionally, we provide a new divergence measure between the source and target domains called Hierarchical Wasserstein distance that indicates under mild assumptions, which structures have to be aligned to lead to a successful adaptation.


page 1

page 2

page 3

page 4


Theoretical Analysis of Domain Adaptation with Optimal Transport

Domain adaptation (DA) is an important and emerging field of machine lea...

Hierarchical Optimal Transport for Unsupervised Domain Adaptation

In this paper, we propose a novel approach for unsupervised domain adapt...

Theoretical Perspective of Deep Domain Adaptation

Deep domain adaptation has recently undergone a big success. Compared wi...

Generalization Bounds for Representative Domain Adaptation

In this paper, we propose a novel framework to analyze the theoretical p...

Concentration bounds for linear Monge mapping estimation and optimal transport domain adaptation

This article investigates the quality of the estimator of the linear Mon...

Learning to Generate Novel Domains for Domain Generalization

This paper focuses on domain generalization (DG), the task of learning f...

Deep Optimal Transport on SPD Manifolds for Domain Adaptation

The domain adaption (DA) problem on symmetric positive definite (SPD) ma...

Please sign up or login with your details

Forgot password? Click here to reset