Background & CV

Download my CV (PDF)

Before joining Inria in Grenoble, I was a postdoctoral researcher in the Department of Statistics at the University of Oxford, working with Patrick Rebeschini. Patrick sparked my interest in policy gradient methods, and our collaboration led to my first paper on the subject, Does Stochastic Gradient really succeed for bandits?, presented as an oral at NeurIPS 2025. I also worked on online convex optimization, including learning in non-stationary environments.

Earlier, I worked with Vianney Perchet in the Inria Fairplay team, based at ENSAE Paris. The team’s energy and breadth of interests made this a particularly stimulating period, with projects at the intersection of machine learning, economics and computer science. My work ranged from structured and constrained bandits to online auctions, optimal stopping and reward lookahead in reinforcement learning.

I received my PhD in Computer Science from the University of Lille, supervised by Emilie Kaufmann and Odalric-Ambrym Maillard in the Inria ScooL team. It was there that I discovered the broader field of reinforcement learning and developed my interest in the theory of sequential decision-making. My thesis focused on non-parametric algorithms for multi-armed bandits, with applications in agriculture and extensions to risk-aware learning and non-stationary environments.

Research visits have also been important in shaping my work. During my PhD, I spent three months at Kyoto University collaborating with Junya Honda. In October 2025, I visited Nicolò Cesa-Bianchi in Milan, where I worked with him and Andrew Jacobsen on bandit convex optimization. This collaboration led to A Perturbation Approach to Unconstrained Linear Bandits, presented at ICML 2026.

Experience

  1. Researcher

    Inria, Université Grenoble-Alpes

    Jul 2025 – Present · Grenoble, France

    Developing theoretical guarantees for reinforcement learning, with a focus on posterior sampling and policy gradient methods. Recent work covers instance-dependent regret in episodic MDPs and the bias of two-timescale stochastic approximation, alongside PhD and internship supervision in the GHOST team.
  2. Research visit

    Collaboration with Nicolò Cesa-Bianchi and Andrew Jacobsen

    Oct 2025 · Milan, Italy

    Visited Nicolò Cesa-Bianchi and worked with him and Andrew Jacobsen, then a postdoctoral researcher in his group, on bandit convex optimization. This collaboration led to a perturbation approach to unconstrained linear bandits (ICML 2026), connecting bandit feedback to online linear optimization.
  3. Post-doctoral researcher

    Department of Statistics, University of Oxford

    Jul 2024 – Jun 2025 · Oxford, United Kingdom

    Patrick Rebeschini introduced me to policy gradient methods, leading to my first paper on stochastic gradient bandits (NeurIPS 2025 Oral). Also developed guarantees for non-stationary bandit convex optimization.
  4. Post-doctoral researcher

    Inria Fairplay, ENSAE, Ecole Polytechnique

    Jan 2023 – Jun 2024 · Palaiseau, France

    With Vianney Perchet, explored a broad range of topics at the intersection of machine learning, economics and computer science in the Fairplay team. Projects included bandits with revenue constraints, learning in uniform-price auctions, optimal stopping and reward lookahead in reinforcement learning.
  5. Visiting student

    Kyoto University

    Apr 2022 – Jul 2022 · Kyoto, Japan

    Worked with Junya Honda on a unified regret analysis of randomized bandit algorithms, bringing Thompson sampling and Minimum Empirical Divergence under a common framework for parametric and non-parametric reward models. Research visit supported by the RELIANT associate team.
  6. Teaching Assistant

    University of Lille

    Jan 2020 – Apr 2022 · Lille, France

    Taught around 150 hours of courses and tutorials in data mining, natural language processing and mathematics for economics, at bachelor’s and master’s levels.
  7. Data Scientist

    Kayrros

    May 2019 – Oct 2019 · Paris, France

    Developed machine learning methods to detect structural changes in energy markets, combining financial time series, news and satellite-derived signals.

Education

  • PhD in Computer Science, 2019-2022

    Université de Lille (Inria Lille, ScooL team)

  • MSc Mathématiques Vision Apprentissage (MVA), 2019

    ENS Paris-Saclay

  • MSc in Statistics and Computer Science, 2019

    ENSAE Paris