Ground Metric Learning on Graphs

by   Matthieu Heitz, et al.

Optimal transport (OT) distances between probability distributions are parameterized by the ground metric they use between observations. Their relevance for real-life applications strongly hinges on whether that ground metric parameter is suitably chosen. Selecting it adaptively and algorithmically from prior knowledge, the so-called ground metric learning GML) problem, has therefore appeared in various settings. We consider it in this paper when the learned metric is constrained to be a geodesic distance on a graph that supports the measures of interest. This imposes a rich structure for candidate metrics, but also enables far more efficient learning procedures when compared to a direct optimization over the space of all metric matrices. We use this setting to tackle an inverse problem stemming from the observation of a density evolving with time: we seek a graph ground metric such that the OT interpolation between the starting and ending densities that result from that ground metric agrees with the observed evolution. This OT dynamic framework is relevant to model natural phenomena exhibiting displacements of mass, such as for instance the evolution of the color palette induced by the modification of lighting and materials.


page 8

page 9

page 10

page 12

page 13

page 14

page 15


Ground Metric Learning

Transportation distances have been used for more than a decade now in ma...

On The Chain Rule Optimal Transport Distance

We define a novel class of distances between statistical multivariate di...

Riemannian Metric Learning via Optimal Transport

We introduce an optimal transport-based model for learning a metric tens...

Unsupervised Ground Metric Learning using Wasserstein Eigenvectors

Optimal Transport (OT) defines geometrically meaningful "Wasserstein" di...

Unbalanced Optimal Transport using Integral Probability Metric Regularization

Unbalanced Optimal Transport (UOT) is the generalization of classical op...

Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics

Optimal transport (OT) is a popular measure to compare probability distr...

Nonlinear Metric Learning through Geodesic Polylinear Interpolation (ML-GPI)

In this paper, we propose a nonlinear distance metric learning scheme ba...