Timezone: »

 
Factored couplings in multi-marginal optimal transport via difference of convex programming
Quang Huy TRAN · Hicham Janati · Ievgen Redko · Rémi Flamary · Nicolas Courty

@
in Optimal Transport and Machine Learning »
Event URL: https://arxiv.org/abs/2110.00629 »

Optimal transport (OT) theory underlies many emerging machine learning (ML) methods nowadays solving a wide range of tasks such as generative modeling, transfer learning and information retrieval. These latter works, however, usually build upon a traditional OT setup with two distributions, while leaving a more general multi-marginal OT formulation somewhat unexplored. In this paper, we study the multi-marginal OT (MMOT) problem and unify several popular OT methods under its umbrella by promoting structural information on the coupling.We show that incorporating such structural information into MMOT results in an instance of a different of convex (DC) programming problem allowing us to solve it numerically. Despite high computational cost of the latter procedure, the solutions provided by DC optimization are usually as qualitative as those obtained using currently employed optimization schemes.

Author Information

Quang Huy TRAN (Université Bretagne Sud)
Hicham Janati (Inria / ENSAE)
Ievgen Redko (Hubert Curien laboratory)
Rémi Flamary (École Polytechnique)
Nicolas Courty (IRISA / University South Brittany)

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

More from the Same Authors