Dependent mixtures of geometric weights priors

DOI10.1016/J.CSDA.2017.09.006zbMATH Open1469.62077arXiv1701.07776OpenAlexW2580463923MaRDI QIDQ1662082FDOQ1662082

Authors: Spyridon J. Hatjispyros, Christos Merkatas, Theodoros Nicoleris, Stephen G. Walker 

Publication date: 17 August 2018

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Abstract: A new approach on the joint estimation of partially exchangeable observations is presented by constructing pairwise dependence between $m$ random density functions, each of which is modeled as a mixture of geometric stick breaking processes. This approach is based on a new random central masses version of the Pairwise Dependent Dirichlet Process prior mixture model (PDDP) first introduced in Hatjispyros et al. (2011). The idea is to create pairwise dependence through random measures that are location-preserving-expectations of Dirichlet random measures. Our contention is that mixture modeling with Pairwise Dependent Geometric Stick Breaking Process (PDGSBP) priors is sufficient for prediction and estimation purposes; moreover the associated Gibbs sampler is much faster and easier to implement than its Dirichlet Process based counterpart. To this respect, we provide a-priori-synchronized comparison studies under sparse $m$-scalable synthetic and real data examples.

Full work available at URL: https://arxiv.org/abs/1701.07776

Recommendations

• Dependent mixtures of Dirichlet processes
• Beta-binomial stick-breaking non-parametric prior
• Dependent mixture models: clustering and borrowing information
• The local Dirichlet process
• On the inferential implications of decreasing weight structures in mixture models

zbMATH Keywords

Bayesian nonparametric inferencemixture of Dirichlet processdependent processgeometric stick breaking mixturesgeometric stick breaking weights

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Nonparametric estimation (62G05)

Cites Work

• Sampling the Dirichlet Mixture Model with Slices
• Kernel stick-breaking processes
• An ANOVA Model for Dependent Random Measures
• Order-Based Dependent Dirichlet Processes
• A Bayesian analysis of some nonparametric problems
• A Method for Combining Inference Across Related Nonparametric Bayesian Models
• Title not available (Why is that?)
• On a class of Bayesian nonparametric estimates: I. Density estimates
• A nonparametric dependent process for Bayesian regression
• Geometric stick-breaking processes for continuous-time Bayesian nonparametric modeling
• Comparing Distributions by using Dependent Normalized Random-Measure Mixtures
• Bayesian inference with dependent normalized completely random measures
• A new Bayesian nonparametric mixture model
• On Bayesian nonparametric modelling of two correlated distributions
• A Bayesian nonparametric estimator of a multivariate survival function
• Dependent mixtures of Dirichlet processes
• Dependent mixture models: clustering and borrowing information
• Random density functions with common atoms and pairwise dependence

Cited In (6)

• System identification using autoregressive Bayesian neural networks with nonparametric noise models
• Joint reconstruction and prediction\break of random dynamical systems under\break borrowing of strength
• The semi-hierarchical Dirichlet process and its application to clustering homogeneous distributions
• Beta-binomial stick-breaking non-parametric prior
• Asymptotic behavior of the number of distinct values in a sample from the geometric stick-breaking process
• On the inferential implications of decreasing weight structures in mixture models

This page was built for publication: Dependent mixtures of geometric weights priors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1662082)