Bonjour — I'm Antoine
I'm broadly interested in the mathematical and algorithmic aspects of deep learning.
-
Postdoc @ EPFL (with Nicolas Boumal) Dec 2024 – present
-
PhD @ ENS Lyon (with Rémi Gribonval, Elisa Riccietti, Nicolas Brisebarre) 2021 – 2024
What I work on
I like working on projects that involve:
- ◈ respecting the structure and geometry of problems (e.g., invariances in theory/algorithms; structured sparsity for efficiency)
- △ investigating minimal setups that still capture key large-scale effects (see dimension one).
Across these projects, a recurring goal is:
- ⇆ bringing theory closer to practice, to better understand, inform, or improve empirical methods