The topography of multivariate normal mixtures

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.

Published at http://dx.doi.org/10.1214/009053605000000417 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (20)

• Nonparametric Density Estimation for High-Dimensional Data - Algorithms and Applications
• A Bayesian Federated Learning Framework with Online Laplace Approximation
• A Population Background for Nonparametric Density-Based Clustering
• Asymptotic theory for density ridges
• Vision-Guided Robot Hearing
• Euler integration over definable functions
• Maximum Number of Modes of Gaussian Mixtures
• Clusters and water flows: a novel approach to modal clustering through Morse theory
• Clustering Via Nonparametric Density Estimation: the R Package pdfCluster
• High dimensional Sparse Gaussian Graphical Mixture Model
• Uncertainty Measures and Limiting Distributions for Filament Estimation
• Nonparametric and Varying Coefficient Modal Regression
• A Formal Model for Adaptive Free Choice in Complex Systems
• Skeleton Clustering: Dimension-Free Density-based Clustering
• Multivariate, Heteroscedastic Empirical Bayes via Nonparametric Maximum Likelihood
• Beyond the Median Voter: A Model of How the Ideological Dimension Shapes Party Polarization
• Dimension reduction for data of unknown cluster structure
• Mixture model modal clustering
• Semi-parametric Bayesian Partially Identified Models based on Support Function
• Inference for Multivariate Normal Mixtures