This paper concerns the introduction of a new Markov Chain Monte Carlo scheme for posterior sampling in Bayesian nonparametric mixture models with priors that belong to the general Poisson-Kingman class. We present a novel compact way of representing the infinite dimensional component of the model such that while explicitly representing this infinite component it has less memory and storage re- quirements than previous MCMC schemes. We describe comparative simulation results demonstrating the efficacy of the proposed MCMC algorithm against ex- isting marginal and conditional MCMC samplers.
A hybrid sampler for Poisson-Kingman mixture models
FAVARO, STEFANO;
2015-01-01
Abstract
This paper concerns the introduction of a new Markov Chain Monte Carlo scheme for posterior sampling in Bayesian nonparametric mixture models with priors that belong to the general Poisson-Kingman class. We present a novel compact way of representing the infinite dimensional component of the model such that while explicitly representing this infinite component it has less memory and storage re- quirements than previous MCMC schemes. We describe comparative simulation results demonstrating the efficacy of the proposed MCMC algorithm against ex- isting marginal and conditional MCMC samplers.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
5799-a-hybrid-sampler-for-poisson-kingman-mixture-models.pdf
Accesso aperto
Tipo di file:
POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione
300.89 kB
Formato
Adobe PDF
|
300.89 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.