Sampling from Dirichlet process mixture models with unknown concentration parameter: mixing issues in large data implementations

DOI10.1007/S11222-014-9471-3zbMATH Open1332.62093DBLPjournals/sac/HastieLR15arXiv1304.1778OpenAlexW1966851795WikidataQ30990753 ScholiaQ30990753MaRDI QIDQ261044FDOQ261044

Authors: David I. Hastie, Silvia Liverani, Sylvia Richardson 

Publication date: 22 March 2016

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: We consider the question of Markov chain Monte Carlo sampling from a general stick-breaking Dirichlet process mixture model, with concentration parameter alpha. This paper introduces a Gibbs sampling algorithm that combines the slice sampling approach of Walker (2007) and the retrospective sampling approach of Papaspiliopoulos and Roberts (2008). Our general algorithm is implemented as efficient open source C++ software, available as an R package, and is based on a blocking strategy similar to that suggested by Papaspiliopoulos (2008) and implemented by Yau et al (2011). We discuss the difficulties of achieving good mixing in MCMC samplers of this nature and investigate sensitivity to initialisation. We additionally consider the challenges when an additional layer of hierarchy is added such that joint inference is to be made on alpha. We introduce a new label switching move and compute the marginal model posterior to help to surmount these difficulties. Our work is illustrated using a profile regression (Molitor et al, 2010) application, where we demonstrate good mixing behaviour for both synthetic and real examples.

Full work available at URL: https://arxiv.org/abs/1304.1778

Recommendations

• Sampling the Dirichlet Mixture Model with Slices
• Slice sampling mixture models
• Sampling schemes for generalized linear Dirichlet process random effects models
• Retrospective Markov chain Monte Carlo methods for Dirichlet process hierarchical models
• MCMC for normalized random measure mixture models

zbMATH Keywords

mixture modelBayesian clusteringDirichlet processprofile regression

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Bayesian inference (62F15) Sampling theory, sample surveys (62D05) Random measures (60G57)

Cites Work

• Bayesian Density Estimation and Inference Using Mixtures
• Markov chain Monte Carlo methods and the label switching problem in Bayesian mixture modeling
• Bayesian profile regression with an application to the National survey of children's health
• Sampling the Dirichlet Mixture Model with Slices
• Title not available (Why is that?)
• Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems
• A Bayesian analysis of some nonparametric problems
• Improved criteria for clustering based on the posterior similarity matrix
• The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator
• Title not available (Why is that?)
• Splitting and merging components of a nonconjugate Dirichlet process mixture model
• Slice sampling mixture models
• Retrospective Markov chain Monte Carlo methods for Dirichlet process hierarchical models
• Ferguson distributions via Polya urn schemes
• Gibbs Sampling Methods for Stick-Breaking Priors
• Nonparametric Bayes local partition models for random effects
• Bayesian Non-Parametric Hidden Markov Models with Applications in Genomics
• Bayesian Semiparametric Joint Models for Functional Predictors
• Bayesian Inference on Changes in Response Densities Over Predictor Clusters

Cited In (14)

• AdaptSPEC-X: Covariate-Dependent Spectral Modeling of Multiple Nonstationary Time Series
• Sampling schemes for generalized linear Dirichlet process random effects models
• Study of hybrid sampling inference for Dirichlet process mixtures of Gaussian processes models
• Infinite mixtures of infinite factor analysers
• Sampling the Dirichlet Mixture Model with Slices
• Revealing Subgroup Structure in Ranked Data Using a Bayesian WAND
• Quantifying the uncertainty of partitions for infinite mixture models
• PReMiuM
• Retrospective Markov chain Monte Carlo methods for Dirichlet process hierarchical models
• Functional non-parametric latent block model: a multivariate time series clustering approach for autonomous driving validation
• Bayesian Spline-Based Hidden Markov Models with Applications to Actimetry Data and Sleep Analysis
• Optimal Bayesian estimators for latent variable cluster models
• Clustering method for censored and collinear survival data
• Slice sampling mixture models

Uses Software

• R

This page was built for publication: Sampling from Dirichlet process mixture models with unknown concentration parameter: mixing issues in large data implementations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q261044)