Conferences

Une journée de conférence organisée par les deux groupes thématiques SIGMA (Signal-Image) et MODE (Optimisation) de la SMAI aura lieu à INRIA Paris mardi 30 janvier 2024: huit exposés de recherche sur des thèmes communs. Inscription gratuite et obligatoire.

A five days conference with introductory lectures in the format of Oberwolfach seminars, 19 – 25 November 2023, Mathematisches Forschungsinstitut Oberwolfach.

A two days conference centered on computational optimal transport and its applications, September 14th-15th, University Gustave Eiffel, Paris area.

Projects

Conference: New Monge Problems and Applications

A two days conference centered on computational optimal transport and its applications, September 14th-15th, University Gustave Eiffel, …

Séances du groupe de travail

Page du groupe de travail du labex Bézout sur les problèmes de transport optimal: Transport martingale, transport optimal faible, …

Posts

Sinkhorn algorithm (also called IPFP for Iterative Proportional Fitting Procedure) is an alternating optimisation algorithm which has …

When trying to understand the low temperature asymptotic of entropic regularization in optimal transport, Gibbs measures naturally …

In a couple of recent papers on applied optimal transport (OT), we used the fact that the so-called semi-dual formulation of OT …

In a project with a student, I recently derived a non-local diffusion PDE which turns out, surprisingly for me, to have a name: Stein …

Recent preprints and publications

Complete list of publications here.

We extend to infinite dimensions the notion of nonnegative cross-curvature introduced by Kim and McCann, several examples are provided.

Time discrete entropic regularization properly renormalized converge to specific entropy regularization of the diffusion coefficients

SGD with decreasing entropic regularization on semi-discrete OT is efficient! In this work, (i) we prove an O(1/t) lower bound rate for …

We study the convergence of gradient flow for the training of deep neural networks. If Residual Neural Networks are a popular example …

We prove global convergence of the Wasserstein gradient flow for the MMD discrepancy with the Coulomb kernel for measures whose …

Talks

In this talk, we insist on the concept of nonnegative cross-curvature and its synthetic definition for a general cost on a product space. Then, by using a formal argument we show why one can expect that such a property should be also true for the Wasserstein space. Then, we give examples of cost satisfying this synthetic nonnegative cross-curvature, in particular a new one with the Bures-Wasserstein case. We extend the result to the case of unbalanced optimal transport and show some potential applications.

In this talk, we study the gradient flow with respect to the Wasserstein metric of the Maximum Mean Discrepancy associated with the Coulomb kernel. In this context, we present several sufficient conditions for global convergence of the gradient flow to the unique global minimum. For instance, on closed Riemannian manifolds, we prove that the so-called Polyak-Lojasiewicz condition holds in some cases, resulting in an exponential convergence. To obtain this result, we use standard estimates from potential theory. An other result is the fact that there is no local minimum apart from the global one. This result is proven using flow interchange techniques.

In this talk, we present our use of the conic formulation first proposed by Liero, Mielke and Savaré, in different applications related to unbalanced optimal transport: the first one is regularity of optimal transport, the second is the Camassa-Holm equation which is the fluid dynamic model directly related to unbalanced optimal transport and the metric on metric measures spaces with unnormalized measures.

Experience

 
 
 
 
 

Professor

Université Gustave Eiffel

Sep 2018 – Present Noisy-Champs
Member of the research lab LIGM (Laboratoire d’informatique Gaspard Monge) and teaching signal processing.
 
 
 
 
 

Assistant professor

University Paris-Dauphine

Sep 2011 – Sep 2018 Paris
Member of the research lab Ceremade, UMR CNRS 7534, and teaching applied mathematics.
 
 
 
 
 

Research assistant

Imperial College

May 2009 – Sep 2011 London
Member of the Institute for Mathematical Sciences and the Math department.
 
 
 
 
 

PhD candidate

ENS Cachan (ENS Paris-Saclay)

Sep 2005 – May 2009 Paris area
Member of the lab CMLA.

PhD and HDR

Habilitation à diriger les recherches

Optimal transport, Diffeomorphisms and applications to imaging

PhD in applied mathematics

Hamiltonian formulation of diffeomorphic image matching