Le lundi 09 mai 2016 à 15:00 - UM - Bât 09 - Salle de conférence (1er étage)Emile Contal
Chaining is known for years to be a powerful tool to study the supremum of stochastic processes. Yet, it did not appear in statistical learning techniques since very recently. In this talk we analyse Bayesian optimization in light of the geometry of Gaussian processes for their canonical distances. We show how chaining can be translated in efficient adaptive algorithms. We will present theoretical guarantees on the regret of the obtained method as well as numerical experiments.