Theoretical Analysis of Domain Adaptation with Optimal Transport
This work addresses domain adaptation for machine learning practitioners dealing with distribution shifts, but it is incremental as it builds on existing theoretical frameworks.
The paper tackles the problem of domain adaptation by theoretically analyzing the use of the Wasserstein metric from optimal transport as a divergence measure between source and target distributions, showing it can provide generalization guarantees for three learning settings and potentially tighter analysis than existing frameworks.
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.