Short bio
Ecole Polytechnique – MVA
Thesis topic
Non-convex optimization and learning theory with kernel methods.
Short abstract
Kernel methods are a versatile tool to study the statistical properties of a vast category of learning algorithm. On one hand, we aim at understanding the generalisation properties of neural network. This enable to design new and more efficient learning routines. On the other, we tackle non-convex optimisation problems through kernel sum-of-squares.