Résumé : Mixture models are widely used in Bayesian statistics and machine learning and proved their efficiency in many fields such as computational biology or natural language processing... Variational inference, a technique for approximating intractable posteriors thanks to optimization algorithms, is extremely popular in practice when dealing with complex models such as mixtures. The contribution of this paper is two-fold. First, we study the concentration of variational approximations of posteriors, which is still an open problem for general mixtures, and we derive consistency and rates of convergence. We also tackle the problem of model selection for the number of components : we study the approach already used in practice, which consists in maximizing a numerical criterion (ELBO). We prove that this strategy indeed leads to strong oracle inequalities. We illustrate our theoretical results by applications to Gaussian and multinomial mixtures.
![]()
Département de Mathématiques
Bâtiment 307
Faculté des Sciences d'Orsay Université Paris-Sud F-91405 Orsay Cedex Tél. : +33 (0) 1-69-15-79-56
Département
Actualités
Les membres
Contacts
Présentation en images des maths à Orsay
Les Maths à Orsay de 1958 à nos jours
Diffusion des mathématiques
Offres d’emploi
Comité Parité du LMO
Fermeture du département
Fermeture du département
Laboratoire
|