Gromov-Wasserstein Averaging of Kernel and Distance Matrices

Abstract : This paper presents a new technique for computing the barycenter of a set of distance or kernel matrices. These matrices, which define the interrelationships between points sampled from individual domains, are not required to have the same size or to be in row-by-row correspondence. We compare these matrices using the softassign criterion , which measures the minimum distortion induced by a probabilistic map from the rows of one similarity matrix to the rows of another; this criterion amounts to a regularized version of the Gromov-Wasserstein (GW) distance between metric-measure spaces. The barycenter is then defined as a Fréchet mean of the input matrices with respect to this criterion, minimizing a weighted sum of softassign values. We provide a fast iterative algorithm for the resulting noncon-vex optimization problem, built upon state-of-the-art tools for regularized optimal transportation. We demonstrate its application to the computation of shape barycenters and to the prediction of energy levels from molecular configurations in quantum chemistry.
Type de document :
Communication dans un congrès
ICML 2016, Jun 2016, New-York, United States. Proc. 33rd International Conference on Machine Learning 〈http://icml.cc/2016/〉
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01322992
Contributeur : Gabriel Peyré <>
Soumis le : vendredi 3 juin 2016 - 01:15:51
Dernière modification le : mercredi 28 septembre 2016 - 16:14:50
Document(s) archivé(s) le : dimanche 4 septembre 2016 - 10:15:24

Fichier

GWBarycentersICML16.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01322992, version 1

Collections

Citation

Gabriel Peyré, Marco Cuturi, Justin Solomon. Gromov-Wasserstein Averaging of Kernel and Distance Matrices. ICML 2016, Jun 2016, New-York, United States. Proc. 33rd International Conference on Machine Learning 〈http://icml.cc/2016/〉. 〈hal-01322992〉

Partager

Métriques

Consultations de
la notice

836

Téléchargements du document

693