Bayesian nonparametric mixtures inconsistency for the number of clusters - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Bayesian nonparametric mixtures inconsistency for the number of clusters

Abstract

Bayesian nonparametric mixture models are often employed for modelling complex data. While these models are well-suited for density estimation, their application for clustering has some limitations. Miller and Harrison (2014) proved posterior inconsistency in the number of clusters when the true number of clusters is finite for Dirichlet process and Pitman–Yor process mixture models. In this work, we extend this result to additional Bayesian nonparametric priors such as Gibbs-type processes and finite-dimensional representations of them. The latter include the Dirichlet multinomial process and the recently emerged Pitman–Yor and normalized generalized gamma multinomial processes. We show that mixture models based on these processes are also inconsistent in the number of clusters.
Fichier principal
Vignette du fichier
JDS___Bayesian_nonparametric_mixtures_inconsistency_for_the_number_of_clusters.pdf (224.89 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03866522 , version 1 (22-11-2022)

Identifiers

  • HAL Id : hal-03866522 , version 1

Cite

Louise Alamichel, Julyan Arbel, Daria Bystrova, Guillaume Kon Kam King. Bayesian nonparametric mixtures inconsistency for the number of clusters. 53es journées de Statistiques, Société Française de Statistique, Jun 2022, Lyon, France. ⟨hal-03866522⟩
35 View
15 Download

Share

Gmail Facebook X LinkedIn More