Bayesian nonparametric mixture of experts for high-dimensional inverse problems - Laboratoire Jean Kuntzmann Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Bayesian nonparametric mixture of experts for high-dimensional inverse problems

Résumé

A large class of problems can be formulated as inverse problems, where the goal is to find parameter values that best explain some observed measures. Typical constraints in practice are that the relationships between parameters and observations are highly nonlinear, with high-dimensional observations and multi-dimensionally correlated parameters. To deal with these constraints, we consider probabilistic mixtures of locally linear models using inverse regression strategies, namely the Gaussian locally linear mapping (GLLiM) models. These can be seen as special instances of a mixture of experts (MoE) models. The popularity of MoE is largely due to their universal approximation properties, provided that the number of mixture components is large enough. In this paper, we propose a general scheme to design a tractable Bayesian nonparametric GLLiM (BNP-GLLiM) model to avoid any commitment to an arbitrary number of components. A tractable estimation algorithm is designed using a variational Bayesian expectation-maximization. In particular, we establish posterior consistency for the number of components in BNP-GLLiM after the merge-truncate-merge algorithm post-processing. Illustrations on simulated data show good results in terms of recovering the true number of clusters and the mean regression function.
Fichier principal
Vignette du fichier
BNP_GLLiM.pdf (1.05 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04015203 , version 1 (05-03-2023)
hal-04015203 , version 2 (01-11-2023)

Identifiants

  • HAL Id : hal-04015203 , version 1

Citer

Trungtin Nguyen, Florence Forbes, Julyan Arbel, Hien Duy Nguyen. Bayesian nonparametric mixture of experts for high-dimensional inverse problems. 2023. ⟨hal-04015203v1⟩
169 Consultations
146 Téléchargements

Partager

Gmail Facebook X LinkedIn More