Short bio
- Master in Probability and Statistics (Université d’Orsay)
- Master in Soft Matter Physics (ICFP)
Thesis title
Energy Landscapes and Dynamics of Deep Neural Networks.
Short abstract
Despite the breakthrough of machine learning in the past decades, the theory behind neural networks and their learning dynamics is still poorly understood compared to their practical achievement in various domains. One promising approach is to rely on the strong analogy between the behaviors of physical disordered systems and deep neural networks. The goal of this PhD is to combine applied mathematics and statistical physics tools in order to solve optimization problems in high dimension. More precisely, the student will focus on the learning dynamics of deep neural networks by using methods inspired from spin glasses theory.