I am currently a postdoctoral researcher in the Department of Statistics at the University of Oxford, working with Patrick Rebeschini on online learning and optimization. In July 2025, I will start a new position as a permanent researcher at Inria Grenoble in the new Ghost team (formerly Polaris).
Prior to that, I was a postdoctoral researcher at the Inria Fairplay team, based at ENSAE Paris, collaborating with Vianney Perchet. My work focused on online algorithms and bandit models, particularly in structured and constrained problem settings, with practical applications in online advertising and recommendation systems.
I received my PhD in Computer Science from the University of Lille, where I worked under the direction of Emilie Kaufmann and Odalric-Ambrym Maillard in the INRIA ScooL team. My PhD research focused on non-parametric algorithms for the Multi-Armed Bandit problem, motivated by an application in agriculture. I explored several approaches based on sub-sampling or bootstrapping, designed to work under realistic non-parametric assumptions on the reward distributions. I then extended these works to address practical considerations: risk-aware learning, non-stationarity of rewards, and batched feedback. During my PhD, I also had the privilege to visit Pr. Junya Honda at the University of Kyoto for 3 months, where I further explored the connection between different families of bandit algorithms.
PhD in Computer Science, 2019-2022
CNRS/Inria Lille, SequeL/ScooL team
MSc Mathématiques Vision Apprentissage (MVA), 2019
ENS Paris-Saclay
MSc in Statistics and Computer Science, 2019
ENSAE Paris