Regularized Optimal Transport and the ROT Mover's Distance

Abstract : This paper presents a unified framework for smooth convex regularization of discrete optimal transport problems. In this context, the regularized optimal transport turns out to be equivalent to a matrix nearness problem with respect to Bregman divergences. Our framework thus naturally generalizes a previously proposed regularization based on the Boltzmann-Shannon entropy related to the Kullback-Leibler divergence, and solved with the Sinkhorn-Knopp algorithm. We call the regularized optimal transport distance the rot mover's distance in reference to the classical earth mover's distance. By exploiting alternate Bregman projections, we develop the alternate scaling algorithm and non-negative alternate scaling algorithm, to compute efficiently the regularized optimal plans depending on whether the domain of the regularizer lies within the non-negative orthant or not. We further enhance the separable case with a sparse extension to deal with high data dimensions. We also instantiate our framework and discuss the inherent specificities for well-known regularizers and statistical divergences in the machine learning and information geometry communities. Finally, we demonstrate the merits of our methods with experiments using synthetic data to illustrate the effect of different regularizers, penalties and dimensions, as well as real-world data for a pattern recognition application to audio scene classification.
Type de document :
Article dans une revue
Journal of Machine Learning Research, Journal of Machine Learning Research, 2018
Liste complète des métadonnées
Contributeur : Nicolas Papadakis <>
Soumis le : samedi 14 juillet 2018 - 21:57:47
Dernière modification le : mercredi 12 septembre 2018 - 12:39:30
Document(s) archivé(s) le : mardi 16 octobre 2018 - 01:13:31


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01540866, version 1
  • ARXIV : 1610.06447



Arnaud Dessein, Nicolas Papadakis, Jean-Luc Rouas. Regularized Optimal Transport and the ROT Mover's Distance. Journal of Machine Learning Research, Journal of Machine Learning Research, 2018. 〈hal-01540866〉



Consultations de la notice


Téléchargements de fichiers