Gromov-Wasserstein Averaging of Kernel and Distance Matrices - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Gromov-Wasserstein Averaging of Kernel and Distance Matrices


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.
Fichier principal
Vignette du fichier
GWBarycentersICML16.pdf (3.95 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01322992 , version 1 (03-06-2016)


  • HAL Id : hal-01322992 , version 1


Gabriel Peyré, Marco Cuturi, Justin Solomon. Gromov-Wasserstein Averaging of Kernel and Distance Matrices. ICML 2016, Jun 2016, New-York, United States. ⟨hal-01322992⟩
2190 View
1450 Download


Gmail Facebook X LinkedIn More