English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The Dirichlet Process Mixture Model (DPMM) is a Bayesian non-parametricapproach widely used for density estimation and clustering. In this manuscript,we study the choice of prior for the variance or precision matrix when Gaussiankernels are adopted. Typically, in the relevant literature, the assessment ofmixture models is done by considering observations in a space of only a handfulof dimensions. Instead, we are concerned with more realistic problems of higherdimensionality, in a space of up to 20 dimensions. We observe that the choiceof prior is increasingly important as the dimensionality of the problemincreases. After identifying certain undesirable properties of standard priorsin problems of higher dimensionality, we review and implement possiblealternative priors. The most promising priors are identified, as well as otherfactors that affect the convergence of MCMC samplers. Our results show that thechoice of prior is critical for deriving reliable posterior inferences. Thismanuscript offers a thorough overview and comparative investigation intopossible priors, with detailed guidelines for their implementation. Althoughour work focuses on the use of the DPMM in clustering, it is also applicable todensity estimation.

Variance matrix priors for Dirichlet process mixture models with Gaussian kernels