Le prochain Mokameeting aura lieu le mercredi 3 mars 2021 sur Discord à 15h00.
Nous aurons le plaisir d’écouter un exposé de Jason Altschuler (Massachusetts Institute of Technology).
Titre : Computing Wasserstein barycenters: easy or hard?
Résumé : Averaging data distributions is a core subroutine throughout data science. Wasserstein barycenters (a.k.a. Optimal Transport barycenters) provide a natural approach for this problem that captures the geometry of the data, and are central to diverse applications in machine learning, statistics, and computer graphics. Despite considerable attention, it remained unknown whether Wasserstein barycenters can be computed in polynomial time. Our recent work provides a complete answer to this question and reveals a surprising “curse of dimensionality”. In this talk, I will explain these results and how they fit more broadly into our research program on algorithms for “structured” Multimarginal Optimal Transport problems.
Joint work with Enric Boix-Adsera
