Efficient Robust Optimal Transport with Application to Multi-Label Classification
Abstract
Optimal transport (OT) is a powerful geometric tool for comparing two distributions and has been employed in various machine learning applications. In this work, we propose a novel OT formulation that takes feature correlations into account while learning the transport plan between two distributions. We model the feature-feature relationship via a symmetric positive semi-definite Mahalanobis metric in the OT cost function. For a certain class of regularizers on the metric, we show that the optimization strategy can be considerably simplified by exploiting the problem structure. For high-dimensional data, we additionally propose suitable low-dimensional modeling of the Mahalanobis metric. Overall, we view the resulting optimization problem as a non-linear OT problem, which we solve using the Frank-Wolfe algorithm. Empirical results on the discriminative learning setting, such as tag prediction and multi-class classification, illustrate the good performance of our approach.
Keywords
Cite
@article{arxiv.2010.11852,
title = {Efficient Robust Optimal Transport with Application to Multi-Label Classification},
author = {Pratik Jawanpuria and N T V Satyadev and Bamdev Mishra},
journal= {arXiv preprint arXiv:2010.11852},
year = {2021}
}
Comments
Accepted to IEEE CDC 2021