Institut de Mathématiques de Marseille, UMR 7373


Accueil >

Generic acceleration schemes for gradient-based optimization

Vendredi 15 juin 14:00-15:00 - Julien MAIRAL - INRIA Grenoble

Generic acceleration schemes for gradient-based optimization

Résumé : In this talk, we present generic techniques to accelerate gradient-based optimization algorithms. These approaches build upon the inexact proximal point algorithm for minimizing a convex objective function, and consists of approximately solving a sequence of well-chosen auxiliary subproblems, leading to faster convergence for the original problem. We introduce two variants based on Nesterov’s acceleration and Quasi-Newton principles, respectively. One of the key to achieve acceleration in theory and in practice is to solve these sub-problems with appropriate accuracy by using the right stopping criterion and the right warm-start strategy.

JPEG - 21.2 ko

Lieu : CMI, salle de séminaire R164 (1er étage) - I2M - Château-Gombert
39 rue Frédéric Joliot-Curie
13453 Marseille cedex 13

Exporter cet événement

Pour en savoir plus sur cet événement, consultez l'article Séminaire Signal et Apprentissage