Annealed SMC Samplers for Dirichlet Process Mixture Models

Autor:	Ali Taylan Cemgil, Yener Ulker, Bilge Gunsel
Rok vydání:	2010
Předmět:	Mathematical optimization business.industry Monte Carlo method Markov process Density estimation Statistics::Computation Dirichlet process symbols.namesake Kernel (statistics) Simulated annealing symbols Algorithm design Artificial intelligence Particle filter business Algorithm Mathematics
Zdroj:	ICPR
DOI:	10.1109/icpr.2010.688
Popis:	In this work we propose a novel algorithm that approximates sequentially the Dirichlet Process Mixtures (DPM) model posterior. The proposed method takes advantage of the Sequential Monte Carlo (SMC) samplers framework to design an effective annealing procedure that prevents the algorithm to get trapped in a local mode. We evaluate the performance in a Bayesian density estimation problem with unknown number of components. The simulation results suggest that the proposed algorithm represents the target posterior much more accurately and provides significantly smaller Monte Carlo error when compared to particle filtering.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::11955342a3e50d05a19e70cc0ba5e6e3 https://doi.org/10.1109/icpr.2010.688 Zobrazit plný text záznamu