Timezone: »

 
Subspace Detours Meet Gromov-Wasserstein
Clément Bonet · Nicolas Courty · François Septier · Lucas Drumetz

@
in Optimal Transport and Machine Learning »
Event URL: https://arxiv.org/abs/2110.10932 »

In the context of optimal transport methods, the subspace detour approach was recently presented by Muzellec and Cuturi (2019). It consists in building a nearly optimal transport plan in the measures space from an optimal transport plan in a wisely chosen subspace, onto which the original measures are projected. The contribution of this paper is to extend this category of methods to the Gromov-Wasserstein problem, which is a particular type of transport distance involving the inner geometry of the compared distributions. After deriving the associated formalism and properties, we also discuss a specific cost for which we can show connections with the Knothe-Rosenblatt rearrangement. We finally give an experimental illustration on a shape matching problem.

Author Information

Clément Bonet (Université de Bretagne Sud)
Nicolas Courty (IRISA / University South Brittany)
François Septier
Lucas Drumetz (IMT Atlantique)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors