news

Dec 15, 2025 Presented our work on the lon-run behaviour of SGD on non-convex landscapes to the Inria Argo team in Paris (slides).
Dec 10, 2025 Delivered an invited seminar on stochastic optimization in deep learning at Morgan Stanley Machine Learning Research, New York (slides).
Oct 14, 2025 Wrapped up my internship at Morgan Stanley ML Research, New York, where I investigated in-context learning capabilities of LLMs, see our preprint.
May 31, 2025 Completed my PhD internship at Apple Machine Learning Research in Paris, working on uncertainty quantification methods for Large Language Models in Marco Cuturi’s team, see our prepint.
Apr 20, 2025 Our paper “The global convergence time of stochastic gradient descent in non-convex landscapes” was accepted at ICML 2025! Preprint available.
Jan 15, 2025 Released our paper “How does the pretraining distribution shape in-context learning?” - joint work with Ali Hasan from our Morgan Stanley collaboration. Available on arXiv.
Dec 15, 2024 Presented “Invariant measures and SGD asymptotics” at the Séminaire de Probabilités et Statistiques of Nice University. Slides available.
Oct 25, 2024 Released “skwdro: a library for Wasserstein distributionally robust machine learning” - collaborative work with Florian Vincent and my advisors. Available on arXiv.
Oct 22, 2024 Gave a seminar on “Large deviation theory for SGD” at the Séminaire de Statistique of the LPSM lab in Paris. Slides here.
Jun 10, 2024 Excited to share that our paper “What is the long-run distribution of stochastic gradient descent? A large deviations analysis” was accepted at ICML 2024! Paper on arXiv.
May 20, 2024 Presented our deterministic analysis of mirror methods at the SMAI MODE Conference in Marseille. Slides available.
Apr 15, 2024 Our work “The rate of convergence of Bregman proximal methods” was accepted for publication in SIAM Journal on Optimization. Preprint on arXiv.