Séminaire Probabilités et Statistiques
A Theoretical Study of Variational Inference
déc. 2021
Intervenant : Badr-Eddine Cherief-Abdellatif
Institution : University of Oxford
Heure : 15h45 - 16h45
Lieu : 3L15

Bayesian inference provides an attractive learning framework to analyze and to sequentially update knowledge on streaming data, but is rarely computationally feasible in practice. In the recent years, variational inference (VI) has become more and more popular for approximationg intractable posterior distributions in Bayesian statistics and machine learning. Nevertheless, despite promising results in real-life applications, only little attention has been put in the literature towards the theoretical properties of VI. In this talk, we aim to present some recent advances in theory of VI. We will show that VI is consistent under mild conditions and retains the same properties than exact Bayesian inference. We will finally illustrate these results with PAC-Bayes bounds in sparse deep learning.

Voir tous les événements