The topography of multivariate normal mixtures
From MaRDI portal
Classification and discrimination; cluster analysis (statistical aspects) (62H30) Foundations and philosophical topics in statistics (62A01) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Characterization and structure theory of statistical distributions (62E10)
Abstract: Multivariate normal mixtures provide a flexible method of fitting high-dimensional data. It is shown that their topography, in the sense of their key features as a density, can be analyzed rigorously in lower dimensions by use of a ridgeline manifold that contains all critical points, as well as the ridges of the density. A plot of the elevations on the ridgeline shows the key features of the mixed density. In addition, by use of the ridgeline, we uncover a function that determines the number of modes of the mixed density when there are two components being mixed. A followup analysis then gives a curvature function that can be used to prove a set of modality theorems.
Recommendations
- On the upper bound of the number of modes of a multivariate normal mixture
- A Graphical Technique for Determining the Number of Components in a Mixture of Normals
- Multiple modes in densities with normal conditionals
- Mixtures of normal distributions: modality and failure rate
- Multivariate Normal Mixtures: A Fast Consistent Method of Moments
Cites work
- scientific article; zbMATH DE number 3763045 (Why is no real title available?)
- scientific article; zbMATH DE number 2090824 (Why is no real title available?)
- scientific article; zbMATH DE number 3284065 (Why is no real title available?)
- scientific article; zbMATH DE number 3326904 (Why is no real title available?)
- scientific article; zbMATH DE number 3052156 (Why is no real title available?)
- Finite mixture models
- ML estimation of the multivariate t distribution and the EM algorithm
- Mixtures with a limited number of modal intervals
- Morse Theory. (AM-51)
- On the Modes of a Mixture of Two Normal Distributions
- The geometry of mixture likelihoods, part II: The exponential family
Cited in
(44)- On the choice of high-dimensional regression parameters in Gaussian random tomography
- Finite mixture models and model-based clustering
- Topological features of multivariate distributions: dependency on the covariance matrix
- Computational aspects of fitting mixture models via the expectation-maximization algorithm
- Inference for multivariate normal mixtures
- Skeleton Clustering: Dimension-Free Density-Aided Clustering
- Mixture model modal clustering
- Kernels, degrees of freedom, and power properties of quadratic distance goodness-of-fit tests
- On the upper bound of the number of modes of a multivariate normal mixture
- Nonparametric statistical learning based on modal regression
- A Review on Modal Clustering
- Estimation of conditional power in the presence of auxiliary data
- Analytical expression for the integrated squared density partial derivative of a multivariate normal mixture distribution
- A likelihood ratio test for bimodality in two-component mixtures with application to regional income distribution in the EU
- Modal non‐linear regression in the presence of Laplace measurement error
- Add isotropic Gaussian kernels at own risk: more and more resilient modes in higher dimensions
- Identifying the number of components in Gaussian mixture models using numerical algebraic geometry
- Online learning of single- and multivalued functions with an infinite mixture of linear experts
- Clusterability assessment for Gaussian mixture models
- The Modal Age of Statistics
- Hidden Markov models with state-dependent mixtures: minimal representation, model testing and applications to clustering
- Finding cluster centers and sizes via multinomial parameterization
- The modality of skew \(t\)-distribution
- A confusion index for measuring separation and clustering
- Max-Linear Competing Factor Models
- Investigating the multimodality of multivariate data with principal curves
- Finite mixtures of unimodal beta and gamma densities and the \(k\)-bumps algorithm
- Dimensionality reduction for data of unknown cluster structure
- When does a mixture of products contain a product of mixtures?
- Fast Bayesian inversion for high dimensional inverse problems
- Methods for merging Gaussian mixture components
- A new regression model: modal linear regression
- On the relation between the linear factor model and the latent profile model
- Likelihood Ratio Testing for Hidden Markov Models Under Non‐standard Conditions
- Asymptotic theory for density ridges
- Incorporating multi-dimensional tail dependencies in the valuation of credit derivatives
- Mode merging for the finite mixture of \(t\)-distributions
- Data-driven robust chance constrained problems: a mixture model approach
- A sufficient condition for the convergence of the mean shift algorithm with Gaussian kernel
- On the distribution of posterior probabilities in finite mixture models with application in clustering
- A population background for nonparametric density-based clustering
- The topological foundation and some properties of the mixed estimator
- Merging the components of a finite mixture using posterior probabilities
- Unimodal category and the monotonicity conjecture
This page was built for publication: The topography of multivariate normal mixtures
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2368846)
