BONNAIRE Tony

Machine learning and statistical physics

École Normale Supérieure - PSL

tony.bonnaire [at] ens.fr

Short bio

PhD in Astrophysics at Université Paris-Saclay

Research project

Machine learning and statistical physics

Short abstract

My current research focuses on understanding the dynamics of simple neural networks and particularly how gradient descent can achieve good generalization, especially when initialized randomly, in high-dimensional, rough and non-convex landscapes. For this purpose, I use methods coming from theoretical physics, and more precisely the statistical physics of disordered systems, to obtain asymptotic success conditions for these methods but also to study the topological properties of the random landscapes.