About me
I am a researcher in the CELESTE team of INRIA Paris-Saclay, located in the Laboratoire Mathématique d’Orsay. I am working on different aspects of the theory of machine learning, including decentralised (online) learning, meta-learning and the theoretical understanding of neural networks.
From October 2021 to March 2023, I was a postdoc in the Theory of Machine Learning Lab at EPFL with Nicolas Flammarion.
In 2021, I completed a PhD at ENS Paris-Saclay, started in September 2018 under the supervision of Vianney Perchet and entitled “Statistical Learning in a strategical environment”. I studied multi-agent learning, combining (online) learning with game theoretical tools. In particular, I mainly focused on the problem of Multiplayer Multi-armed bandits.
Have a look at my (hopefully updated) CV for additional information!
Please, do not hesitate to ask me any question or supplementary material (code, slides…) by email.
News
- I was invited to the Symposium on Sparsity and Singular Structures in Aachen to talk about our latest work Early alignment in two-layer networks training is a two-edged sword. You can have a look at the slides here. 28-02-2024
- I am invited at CIRM for From matching to markets workshop. I will be giving a review of multiplayer bandits. 01-12-2023
- I will be giving a 1h30 lecture on Gradient flow dynamics of shallow ReLU networks at the Analytical Approaches for Neural Network Dynamics workshop. This will happen at Institut Henri Poincaré, on October 23rd. 01-10-2023
- I started a permanent position at INRIA Saclay in the CELESTE team, located at Orsay. If you are interested in a potential internship, PhD, postdoc or even just a collaboration/visiting, do not hesitate to reach out to me! 01-04-2023