Probabilistic relabelling strategies for the label switching problem in Bayesian mixture models

M. Sperrin*, T. Jaki, E. Wit

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

53 Citations (Scopus)
273 Downloads (Pure)

Abstract

The label switching problem is caused by the likelihood of a Bayesian mixture model being invariant to permutations of the labels. The permutation can change multiple times between Markov Chain Monte Carlo (MCMC) iterations making it difficult to infer component-specific parameters of the model. Various so-called 'relabelling' strategies exist with the goal to 'undo' the label switches that have occurred to enable estimation of functions that depend on component-specific parameters. Existing deterministic relabelling algorithms rely upon specifying a loss function, and relabelling by minimising its posterior expected loss. In this paper we develop probabilistic approaches to relabelling that allow for estimation and incorporation of the uncertainty in the relabelling process. Variants of the probabilistic relabelling algorithm are introduced and compared to existing deterministic relabelling algorithms. We demonstrate that the idea of probabilistic relabelling can be expressed in a rigorous framework based on the EM algorithm.

Original languageEnglish
Pages (from-to)357-366
Number of pages10
JournalStatistics and Computing
Volume20
Issue number3
DOIs
Publication statusPublished - Jul-2010

Keywords

  • Bayesian
  • Identifiability
  • Label switching
  • MCMC
  • Mixture model
  • DISTRIBUTIONS

Cite this