Biography
I am a researcher at Criteo, focusing on bandit algorithms and reinforcement learning.
I received my PhD in 2021; I was lucky to be supervised by Olivier Fercoq and Marc Abeille. Recently, I mainly worked on understanding how to learn from structured bandit feedback in non-linear (and non-stationary) environments.
Download my resumé.
- Bandit Algorithms
- Reinforcement Learning
- Machine Learning
-
PhD in Machine Learning, 2021
Télécom Paris
-
MSc in Artificial Intelligence, 2016-2018
Ecole Polytechnique Fédérale de Lausanne (EPFL)
-
MSc in Applied Mathematics, 2013-2018
Ecole Polytechnique
Publications
Experience
- Research on bandit algorithms and reinforcement learning. Focus on the design of new algorithms with strong theoretical guarantees.
- Internal consulting for engineering teams on production projects.
Development of a deep reinforcement learning approach for learning hyper-parameter free optimizers for ML tasks.
🌟 Received maximal mark from EPFL.
- Development of algorithms for the synchronization of mobile robot fleets in warehouses.
- Design, development and implementation of robust and embedded control algorithms for wheeled robots.
🌟 Rewarded as best internship for industrial use by the Prix de la Fondation de l’École Polytechnique.
Recent Talks
Code
