In this paper, we use the class of Wasserstein metrics to study asymptotic properties of posterior distributions. Our first goal is to provide sufficient conditions for posterior consistency. In addition to the well-known Schwartz’s Kullback–Leibler condition on the prior, the true distribution and most probability measures in the support of the prior are required to possess moments up to an order which is determined by the order of the Wasserstein metric. We further investigate convergence rates of the posterior distributions for which we need stronger moment conditions. The required tail conditions are sharp in the sense that the posterior distribution may be inconsistent or contract slowly to the true distribution without these conditions. Our study involves techniques that build on recent advances on Wasserstein convergence of empirical measures. We apply the results to some examples including a Dirichlet process mixture prior and conduct a simulation study for further illustration.

Posterior asymptotics in Wasserstein metrics on the real line

De Blasi, Pierpaolo;
2021

Abstract

In this paper, we use the class of Wasserstein metrics to study asymptotic properties of posterior distributions. Our first goal is to provide sufficient conditions for posterior consistency. In addition to the well-known Schwartz’s Kullback–Leibler condition on the prior, the true distribution and most probability measures in the support of the prior are required to possess moments up to an order which is determined by the order of the Wasserstein metric. We further investigate convergence rates of the posterior distributions for which we need stronger moment conditions. The required tail conditions are sharp in the sense that the posterior distribution may be inconsistent or contract slowly to the true distribution without these conditions. Our study involves techniques that build on recent advances on Wasserstein convergence of empirical measures. We apply the results to some examples including a Dirichlet process mixture prior and conduct a simulation study for further illustration.
ELECTRONIC JOURNAL OF STATISTICS
15
2
3635
3677
https://projecteuclid.org/journals/electronic-journal-of-statistics/volume-15/issue-2/Posterior-asymptotics-in-Wasserstein-metrics-on-the-real-line/10.1214/21-EJS1869.full
Dirichlet process mixture, nonparametric Bayes ian inference, posterior consistency, posterior convergence rate, Wasserstein metrics
Chae, Minwoo; De Blasi, Pierpaolo; Walker, Stephen G.
File in questo prodotto:
File Dimensione Formato  
chae,deblasi,walker-2021_cca.pdf

accesso aperto

Descrizione: Articolo principale
Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 513.52 kB
Formato Adobe PDF
513.52 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2318/1795297
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact