An adaptive truncation method for inference in Bayesian nonparametric models

DOI10.1007/S11222-014-9519-4zbMATH Open1342.62047arXiv1308.2045OpenAlexW2006880521MaRDI QIDQ2631376FDOQ2631376

Authors: J. E. Griffin 

Publication date: 29 July 2016

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

Abstract: Many exact Markov chain Monte Carlo algorithms have been developed for posterior inference in Bayesian nonparametric models which involve infinite-dimensional priors. However, these methods are not generic and special methodology must be developed for different classes of prior or different models. Alternatively, the infinite-dimensional prior can be truncated and standard Markov chain Monte Carlo methods used for inference. However, the error in approximating the infinite-dimensional posterior can be hard to control for many models. This paper describes an adaptive truncation method which allows the level of the truncation to be decided by the algorithm and so can avoid large errors in approximating the posterior. A sequence of truncated priors is constructed which are sampled using Markov chain Monte Carlo methods embedded in a sequential Monte Carlo algorithm. Implementational details for infinite mixture models with stick-breaking priors and normalized random measures with independent increments priors are discussed. The methodology is illustrated on infinite mixture models, a semiparametric linear mixed model and a nonparametric time series model.

Full work available at URL: https://arxiv.org/abs/1308.2045

Recommendations

• Markov chain Monte Carlo in approximate Dirichlet and beta two-parameter process hierarchical models
• Sequential Monte Carlo methods for mixtures with normalized random measures with independent increments priors
• MCMC for normalized random measure mixture models
• Truncated Poisson-Dirichlet approximation for Dirichlet process hierarchical models
• Posterior sampling from \(\epsilon\)-approximation of normalized completely random measure mixtures

zbMATH Keywords

sequential Monte CarloDirichlet processtruncation errorPoisson-Dirichlet processstick-breaking priorsnormalized random measures with independent increments

Mathematics Subject Classification ID

Bayesian inference (62F15) Nonparametric estimation (62G05)

Cites Work

• Sequential Monte Carlo Samplers
• Financial Modelling with Jump Processes
• Bayesian Density Estimation and Inference Using Mixtures
• A Representation of Independent Increment Processes without Gaussian Components
• Sparse Bayesian infinite factor models
• Sampling the Dirichlet Mixture Model with Slices
• A nonparametric model for stationary time series
• Bayesian Semiparametric Median Regression Modeling
• Modeling Regression Error With a Mixture of Polya Trees
• Time-varying sparsity in dynamic regression models
• A Bayesian analysis of some nonparametric problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• SMC2: An Efficient Algorithm for Sequential Analysis of State Space Models
• Monte Carlo strategies in scientific computing
• Prior distributions for variance parameters in hierarchical models (Comment on article by Browne and Draper)
• A sequential particle filter method for static models
• Hierarchical Mixture Modeling With Normalized Inverse-Gaussian Priors
• MCMC for normalized random measure mixture models
• On adaptive Markov chain Monte Carlo algorithms
• The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator
• Default priors for density estimation with mixture models
• A semiparametric Bayesian model for randomised block designs
• Markov chain Monte Carlo in approximate Dirichlet and beta two-parameter process hierarchical models
• Exact and approximate sum representations for the Dirichlet process
• Title not available (Why is that?)
• Slice sampling mixture models
• Bayesian Nonparametrics
• Distributional results for means of normalized random measures with independent increments
• Normalized random measures driven by increasing additive processes
• Posterior Analysis for Normalized Random Measures with Independent Increments
• Gibbs Sampling Methods for Stick-Breaking Priors
• An adaptive sequential Monte Carlo method for approximate Bayesian computation
• On a class of Bayesian nonparametric estimates: I. Density estimates
• Title not available (Why is that?)
• Inference for Lévy-driven stochastic volatility models via adaptive sequential Monte Carlo
• On the convergence of adaptive sequential Monte Carlo methods
• Sequential Monte Carlo on large binary sampling spaces
• Approximating distributions of random functionals of Ferguson-Dirichlet priors
• Controlling the Reinforcement in Bayesian Non-Parametric Mixture Models
• Bayesian density estimation and model selection using nonparametric hierarchical mixtures
• A Semiparametric Bayesian Approach to the Random Effects Model
• On the stick-breaking representation of normalized inverse Gaussian priors
• Bayesian nonparametric analysis for a generalized Dirichlet process prior
• Independent and Identically Distributed Monte Carlo Algorithms for Semiparametric Linear Mixed Models
• Center-adjusted inference for a nonparametric Bayesian random effect distribution
• Semiparametric Bayes hierarchical models with mean and variance constraints
• On asymptotic properties and almost sure approximation of the normalized inverse-Gaussian process
• Local Shrinkage Rules, Lévy Processes and Regularized Regression
• On simulations from the two-parameter Poisson-Dirichlet process and the normalized inverse-Gaussian process

Cited In (13)

• Semiparametric Bayesian analysis for longitudinal mixed effects models with non-normal AR(1) errors
• Distribution on warp maps for alignment of open and closed curves
• Truncated random measures
• A blocked Gibbs sampler for NGG-mixture models via a priori truncation
• Bayesian registration of functions and curves
• A review of uncertainty quantification for density estimation
• Discussion of ``Nonparametric Bayesian inference in applications: Bayesian nonparametric methods in econometrics
• Truncated Poisson-Dirichlet approximation for Dirichlet process hierarchical models
• Truncated simulation and inference in edge-exchangeable networks
• Bayesian nonparametric vector autoregressive models
• An adaptive truncated product method for combining dependent \(p\)-values
• A moment-matching Ferguson \& Klass algorithm
• Colombian women's life patterns: a multivariate density regression approach

This page was built for publication: An adaptive truncation method for inference in Bayesian nonparametric models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2631376)