A Riemannian Newton trust-region method for fitting Gaussian mixture models

DOI10.1007/s11222-021-10071-1zbMath1477.62015arXiv2104.14957OpenAlexW3157127899WikidataQ115380706 ScholiaQ115380706MaRDI QIDQ2066749

Lena Sembach, Jan Pablo Burgard, Volker H. Schulz

Publication date: 14 January 2022

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2104.14957

zbMATH Keywords

clusteringdensity estimationGaussian mixture modelstrust-region methodsmanifold optimization

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Statistics on manifolds (62R30) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Numerical mathematical programming methods (65K05)

Uses Software

• UCI-ml
• PMTK
• Pymanopt
• MixEst
• k-means++
• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On mixtures of skew normal and skew \(t\)-distributions
• A new variational Bayesian algorithm with application to human mobility pattern modeling
• Sensitivity of trust-region algorithms to their parameters
• An interior-point algorithm for nonconvex nonlinear programming
• Addressing overfitting and underfitting in Gaussian model-based clustering
• Simple algorithms for optimization on Riemannian manifolds with constraints
• An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization
• Detecting anomalies in fibre systems using 3-dimensional image data
• A survey and comparison of contemporary algorithms for computing the matrix geometric mean
• Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiation
• A Riemannian trust-region method for low-rank tensor completion
• Automatic Determination of an Initial Trust Region in Nonlinear Programming
• Trust Region Methods
• Automatic Preconditioning by Limited Memory Quasi-Newton Updating
• Using Mixtures in Econometric Models: A Brief Review and Some New Results
• Finite Mixture Models for Mapping Spatially Dependent Disease Counts
• Conic Geometric Optimization on the Manifold of Positive Definite Matrices

This page was built for publication: A Riemannian Newton trust-region method for fitting Gaussian mixture models