Calendrier des événements
Working Group on risk
On the global convergence of gradient descent for non convex machine learning problems
Cette conférence sera animée par le Docteur Francis BACH de l'INRIA.
Abstract
Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study a simple minimization method: the unknown measure is discretized into a mixture of particles and a continuous-time gradient descent is performed on their weights and positions. This is an idealization of the usual way to train neural networks with a large hidden layer. We show that, when initialized correctly and in the many-particle limit, this gradient flow, although non-convex, converges to global minimizers. The proof involves Wasserstein gradient flows, a by-product of optimal transport theory. Numerical experiments show that this asymptotic behavior is already at play for a reasonable number of particles, even in high dimension. (Joint work with Lénaïc Chizat)
Voir tous les événements
Lundi 17 juin 2019
12h30
- 13h30
(GMT +2)
ESSEC
campus La Défense (CNIT) - Salle 202
La Défense
-
Gratuit
Inscriptions closes
ESSEC
campus La Défense (CNIT) - Salle 202La Défense
Aucun commentaire
Vous devez être connecté pour laisser un commentaire. Connectez-vous.