Séminaire Jeunes chercheurs (Quentin Giton, jeudi 15 juin 2026)

La prochaine séance du séminaire Jeunes chercheurs du CEREMADE aura lieu le jeudi 15 juin 2026 à 17h en salle A707. Nous aurons le plaisir d'écouter Quentin Giton (Université Paris-Saclay), qui nous parlera de

Wasserstein gradient flows (and generative modelling).

Abstract
Optimal Transport (OT) equips the space of probability measures with the 2-Wasserstein distance, allowing us to interpret many PDEs as gradient flows of energy functionals. I will first recall the Monge-Kantorovich formulation of OT and the definition of the 2-Wasserstein distance. Then, I will introduce Wasserstein gradient flows, viewing probability measures as densities of point clouds.
If time allows, in the second part, I will present recent work using this framework to drive an unknown initial measure towards a Gaussian reference measure, while learning the associated vector field (the score) along the way. This connects Wasserstein gradient flows with score-based methods, a central objective in many modern generative modelling approaches.