He is an associate professor at Ecole des Ponts ParisTech and a researcher at CERMICS, in the Optimization team. He is interested in the relations between optimization algorithms in finite and infinite dimensions, their convergence properties and the associated notions of convexity. His main playfield is optimization in the space of probability measures, in connection with optimal transport theory and optimal control. Applications of these methods are developed with Axel Parmentier for operations research, working in particular with Air France.

His latest focus is on optimization problems where the notion of distance is replaced by a generic cost function (slides), e.g., Bregman divergences. The natural algorithm here is alternating minimization (article) and the convergence assumptions and limit flow are related to Evolution Variational Inequalities (article). He also works on the characterization of order isomorphisms with Stéphane Gaubert (article and slides).

He was a post-doctoral researcher in 2023-24 at TU Wien VADOR with Aris Daniilidis; in 2021-23 at INRIA SIERRA, with Alessandro Rudi. I obtained my PhD in July 2021 from École des Mines Paris – PSL (Paris), at the CAS laboratory, working on shape/state constraints in optimal control and nonparametric regression through kernel methods (manuscript, slides). He graduated from École polytechnique (X2013) in 2017, then obtained my Master degree (MVA, Mathematics-Vision-Learning) with Highest Honours after an internship on gene network inference (based on single-cell RNA sequencing).

Follow-ups on my PhD tackle the links between kernel methods, optimal control, Kalman filtering and optimization in measure spaces. So far I have shown that kernels appear in linear-quadratic optimal control because of Hilbertian vector spaces of trajectories, while, for estimation problems, they appear through covariances of Gaussian processes. It is this dual, deterministic and stochastic, nature of kernels which underlies the duality between optimal control and estimation in the Linear-Quadratic case (see arXiv, slides with Alain Bensoussan). Kernels even extend to mean-field control (article).

His research and his lyricomania, a passion he shares within the association Juvenilia, do not leave him so much time to spare, but he occasionnaly paints.

• Optimization with general costs
• Flows on measure spaces
• Kernel Methods
• Optimal Control