Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning

Abstract : This article introduces a new non-linear dictionary learning method for histograms in the probability simplex. The method leverages optimal transport theory, in the sense that our aim is to reconstruct histograms using so called displacement interpolations (a.k.a. Wasserstein barycenters) between dictionary atoms; such atoms are themselves synthetic histograms in the probability simplex. Our method simultaneously estimates such atoms, and, for each datapoint, the vector of weights that can optimally reconstruct it as an optimal transport barycenter of such atoms. Our method is computationally tractable thanks to the addition of an entropic regularization to the usual optimal transportation problem, leading to an approximation scheme that is efficient, parallel and simple to differentiate. Both atoms and weights are learned using a gradient-based descent method. Gradients are obtained by automatic differentiation of the generalized Sinkhorn iterations that yield barycenters with entropic smoothing. Because of its formulation relying on Wasserstein barycenters instead of the usual matrix product between dictionary and codes, our method allows for non-linear relationships between atoms and the reconstruction of input data. We illustrate its application in several different image processing settings.
Type de document :
Article dans une revue
SIAM Journal on Imaging Sciences, Society for Industrial and Applied Mathematics, 2018
Liste complète des métadonnées

Littérature citée [76 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01717943
Contributeur : David Coeurjolly <>
Soumis le : lundi 26 février 2018 - 22:31:26
Dernière modification le : mardi 24 avril 2018 - 17:20:06

Identifiants

  • HAL Id : hal-01717943, version 1

Citation

Morgan Schmitz, Matthieu Heitz, Nicolas Bonneel, Fred Maurice Ngolè Mboula, David Coeurjolly, et al.. Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning. SIAM Journal on Imaging Sciences, Society for Industrial and Applied Mathematics, 2018. 〈hal-01717943〉

Partager

Métriques

Consultations de la notice

195

Téléchargements de fichiers

38