Luc Brogat-Motte

I am a postdoctoral researcher at the Istituto Italiano di Tecnologia, working with Lorenzo Rosasco on developing learning methods for stochastic dynamical systems.

Previously, I was a postdoc under the supervision of Riccardo Bonalli (L2S, CentraleSupélec) and Alessandro Rudi (SIERRA team, Inria Paris). I studied the estimation of controlled stochastic differential equations.

Before that, I completed my PhD at Télécom Paris, under the supervision of Florence d'Alché-Buc (Télécom Paris) and Juho Rousu (Aalto University), where I studied statistical learning theory and kernel methods. I developed efficient learning algorithms for predicting complex outputs, including molecular graphs. I received the runner-up prize for the 2024 CSDAI Best PhD Thesis Award at Institut Polytechnique de Paris.

The aim of my research is to understand which structural properties of learning problems matter, quantify the gains they enable, and design algorithms that realize those gains. To this end, I draw on probability, statistics, stochastic processes, and operator theory.

Email: luc.brogatmotte@iit.it

Address: MaLGa Center, Università di Genova, Italia.

CV  /  Scholar  /  GitHub

Publications and Preprints

PhD thesis

Thanks, Jon Barron, for the template.