Nonexchangeable random partition models for microclustering
From MaRDI portal
Publication:2054470
Abstract: Many popular random partition models, such as the Chinese restaurant process and its two-parameter extension, fall in the class of exchangeable random partitions, and have found wide applicability in model-based clustering, population genetics, ecology or network analysis. While the exchangeability assumption is sensible in many cases, it has some strong implications. In particular, Kingman's representation theorem implies that the size of the clusters necessarily grows linearly with the sample size; this feature may be undesirable for some applications, as recently pointed out by Miller et al. (2015). We present here a flexible class of non-exchangeable random partition models which are able to generate partitions whose cluster sizes grow sublinearly with the sample size, and where the growth rate is controlled by one parameter. Along with this result, we provide the asymptotic behaviour of the number of clusters of a given size, and show that the model can exhibit a power-law behavior, controlled by another parameter. The construction is based on completely random measures and a Poisson embedding of the random partition, and inference is performed using a Sequential Monte Carlo algorithm. Additionally, we show how the model can also be directly used to generate sparse multigraphs with power-law degree distributions and degree sequences with sublinear growth. Finally, experiments on real datasets emphasize the usefulness of the approach compared to a two-parameter Chinese restaurant process.
Recommendations
- Random Partition Models for Microclustering Tasks
- Clustering via nonsymmetric partition distributions
- Exchangeable and partially exchangeable random partitions
- Random partition models and exchangeability for Bayesian identification of population struc\-ture
- Random partition models with regression on covariates
Cites work
- scientific article; zbMATH DE number 3896009 (Why is no real title available?)
- scientific article; zbMATH DE number 3518091 (Why is no real title available?)
- scientific article; zbMATH DE number 2017734 (Why is no real title available?)
- scientific article; zbMATH DE number 4000257 (Why is no real title available?)
- scientific article; zbMATH DE number 2106098 (Why is no real title available?)
- scientific article; zbMATH DE number 227027 (Why is no real title available?)
- scientific article; zbMATH DE number 3248623 (Why is no real title available?)
- scientific article; zbMATH DE number 3349081 (Why is no real title available?)
- scientific article; zbMATH DE number 2214054 (Why is no real title available?)
- An Introduction to the Theory of Point Processes
- Bayesian Nonparametric Estimation of the Probability of Discovering New Species
- Bayesian Poisson process partition calculus with an application to Bayesian Lévy moving averages
- Bayesian inference with dependent normalized completely random measures
- Bayesian nonparametric analysis for a generalized Dirichlet process prior
- Beta processes, stick-breaking and power laws
- Combinatorial stochastic processes. Ecole d'Eté de Probabilités de Saint-Flour XXXII -- 2002.
- Completely random measures
- Conditional formulae for Gibbs-type exchangeable random partitions
- Contributions to the theory of Dirichlet processes
- Controlling the Reinforcement in Bayesian Non-Parametric Mixture Models
- Distance dependent chinese restaurant processes
- Distribution theory for hierarchical processes
- Distributional results for means of normalized random measures with independent increments
- Edge exchangeable models for interaction networks
- Exchangeable and partially exchangeable random partitions
- Generalized Gamma measures and shot-noise Cox processes
- Generalized Pólya urn for time-varying Pitman-Yor processes
- Heavy-Tail Phenomena
- Hierarchical Mixture Modeling With Normalized Inverse-Gaussian Priors
- Latent nested nonparametric priors (with discussion)
- Looking-backward probabilities for Gibbs-type exchangeable random partitions
- Nonparametric Bayesian inference.
- Normalized random measures driven by increasing additive processes
- Notes on the occupancy problem with infinitely many boxes: general asymptotics and power laws
- On edge exchangeable random graphs
- Order-Based Dependent Dirichlet Processes
- Particle Markov Chain Monte Carlo Methods
- Posterior Analysis for Normalized Random Measures with Independent Increments
- Power laws for family sizes in a duplication model
- Random partitions in population genetics
- Random permutations with cycle weights
- Sequential Monte Carlo Methods in Practice
- Sequential Monte Carlo Samplers
- Size-biased sampling of Poisson point processes and excursions
- Sparse graphs using exchangeable random measures
- The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator
Cited in
(9)- Clustering via nonsymmetric partition distributions
- Random partition models and complementary clustering of Anglo-Saxon place-names
- An EPPF from independent sequences of geometric random variables
- Asymptotic analysis of statistical estimators related to multigraphex processes under misspecification
- Fast Generation of Exchangeable Sequence of Clusters Data
- Asymptotic behavior of the number of distinct values in a sample from the geometric stick-breaking process
- Interfaces for random cluster models
- Concentration in the generalized Chinese restaurant process
- Random Partition Models for Microclustering Tasks
This page was built for publication: Nonexchangeable random partition models for microclustering
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2054470)
