Infinite Dirichlet Mixture Model and Its Application via Variational Bayes
Wentao Fan, Nizar Bouguila · 2011
In this paper, we propose a Bayesian nonparametric approach for modeling and selection based on the mixture of Dirichlet processes with Dirichlet distributions, which can also be considered as an infinite Dirichlet mixture model. The proposed model adopts a stick-breaking representation of the Dirichlet process and is learned through a variational inference method. In our approach, the determination of the number of clusters is sidestepped by assuming an infinite number of clusters. The effectiveness of our approach is tested on a real application involving unsupervised image categorization.