English

Efficient Robust Optimal Transport with Application to Multi-Label Classification

Machine Learning 2021-10-08 v2 Optimization and Control

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

R2 v1 2026-06-23T19:33:46.698Z