I am a postdoctoral researcher in the Theory of Machine Learning lab at EPFL, working with Nicolas Flammarion on the theoretical foundations of post-training for Large Language Models. My research interests include multi-armed bandits, sequential hypothesis testing, differential privacy, reinforcement learning, imitation learning, online learning, statistics, and optimization. I focus on developing theoretically well-founded and practically applicable algorithms.

I earned my PhD in Computer Science from the University of Lille, under the supervision of Emilie Kaufmann and Rémy Degenne within the Inria Scool team. My research focused on pure exploration problems in stochastic multi-armed bandits. In my thesis, I aimed to establish the Top-Two approach as a principled methodology that offers both near-optimal theoretical guarantees and state-of-the-art empirical performance. I addressed various facets of bandit theory, including parametric and non-parametric distribution classes, structural assumptions on mean rewards, and a range of identification problems. I was honored to receive the runner-up PhD Award from AFIA (French Association for Artificial Intelligence). During my PhD, I also had the opportunity to spend three months at the University of Milan, visiting Nicolò Cesa-Bianchi in the Laboratory for Artificial Intelligence and Learning Algorithms.

Before my PhD, I graduated from Ecole Polytechnique and ETH Zurich. I conducted my Master’s thesis in the Learning & Adaptive Systems group of Andreas Krause, where I studied pure exploration for combinatorial bandits with semi-bandit feedback.