Optimal Bayesian clustering using non-negative matrix factorization
From MaRDI portal
Abstract: Bayesian model-based clustering is a widely applied procedure for discovering groups of related observations in a dataset. These approaches use Bayesian mixture models, estimated with MCMC, which provide posterior samples of the model parameters and clustering partition. While inference on model parameters is well established, inference on the clustering partition is less developed. A new method is developed for estimating the optimal partition from the pairwise posterior similarity matrix generated by a Bayesian cluster model. This approach uses non-negative matrix factorization (NMF) to provide a low-rank approximation to the similarity matrix. The factorization permits hard or soft partitions and is shown to perform better than several popular alternatives under a variety of penalty functions.
Recommendations
Cites work
- scientific article; zbMATH DE number 1085980 (Why is no real title available?)
- A Bayesian analysis of some nonparametric problems
- Bayesian Clustering and Product Partition Models
- Bayesian Density Estimation and Inference Using Mixtures
- Bayesian cluster analysis
- Bayesian cluster analysis: point estimation and credible balls (with discussion)
- Comparing clusterings -- an information based distance
- Controlling the Reinforcement in Bayesian Non-Parametric Mixture Models
- Density Estimation With Confidence Sets Exemplified by Superclusters and Voids in the Galaxies
- Fast nonnegative matrix factorization: an active-set-like method and comparisons
- Ferguson distributions via Polya urn schemes
- Finite mixture models and model-based clustering
- Gibbs Sampling Methods for Stick-Breaking Priors
- Improved criteria for clustering based on the posterior similarity matrix
- Learning the parts of objects by non-negative matrix factorization
- Model-Based Clustering, Discriminant Analysis, and Density Estimation
- Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method
- On the complexity of nonnegative matrix factorization
- Optimal Bayesian estimators for latent variable cluster models
- Projected Gradient Methods for Nonnegative Matrix Factorization
- The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator
- Variable Selection for Clustering with Gaussian Mixture Models
- Variable Selection for Model-Based Clustering
Cited in
(6)- Optimal Bayesian estimators for latent variable cluster models
- A variable neighborhood search heuristic for nonnegative matrix factorization with application to microarray data
- Bayesian nonparametric clustering as a community detection problem
- Clustering via nonsymmetric partition distributions
- Bayesian mean-parameterized nonnegative binary matrix factorization
- Bayesian nonparametric clustering for large data sets
This page was built for publication: Optimal Bayesian clustering using non-negative matrix factorization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1796973)
