Convergence of latent mixing measures in nonparametric and mixture models

Details Convergence of latent mixing measures in nonparametric and mixture models Convergence of latent mixing measures in nonparametric and mixture models

2011-09-15

arxiv.org/abs/1109.3250v3

Mathematics

Statistics Theory

New Theorem 2, strengthened results in Theorem 6 from previous version

Scientific paper

We consider Wasserstein distance functionals for assessing the convergence of latent discrete measures, which serve as mixing distributions in hierarchical and nonparametric mixture models. We clarify the relationships between Wasserstein distances of mixing distributions and $f$-divergence functionals such as Hellinger and Kullback-Leibler distances on the space of mixture distributions using various identifiability conditions. The convergence in Wasserstein metrics for latent discrete mixing measures has a natural interpretation of the convergence of individual atoms that provide support for the discrete measure. It is also typically stronger than the weak convergence induced by standard $f$-divergence metrics. We establish rates of convergence of posterior distributions for latent discrete measures in several mixture models, including finite mixtures of multivariate distributions, finite mixtures of Gaussian processes and infinite mixtures based on the Dirichlet process.

Affiliated with

Also associated with

No associations

Rating

Convergence of latent mixing measures in nonparametric and mixture models does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Convergence of latent mixing measures in nonparametric and mixture models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Convergence of latent mixing measures in nonparametric and mixture models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-672341