Deep Gaussian mixture models

DOI10.1007/S11222-017-9793-ZMaRDI QIDQ88400zbMATH OpenOpenAlexFDO

Authors Cinzia Viroli, Geoffrey J. Mclachlan, Geoffrey J. McLachlan

Publication date 1 December 2017

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

Full work available at URL https://arxiv.org/abs/1711.06929

zbMATH Keywords

mixtures of factor analyzersstochastic EM algorithmunsupervised classification

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Gaussian processes (60G15)

Abstract: Deep learning is a hierarchical inference method formed by subsequent multiple layers of learning able to more efficiently describe complex relationships. In this work, Deep Gaussian Mixture Models are introduced and discussed. A Deep Gaussian Mixture model (DGMM) is a network of multiple layers of latent variables, where, at each layer, the variables follow a mixture of Gaussian distributions. Thus, the deep mixture model consists of a set of nested mixtures of linear models, which globally provide a nonlinear model able to describe the data in a very flexible way. In order to avoid overparameterized solutions, dimension reduction by factor models can be applied at each layer of the architecture thus resulting in deep mixtures of factor analysers.

Recommendations

• Variational inference and sparsity in high-dimensional deep Gaussian mixture models
• How deep are deep Gaussian processes?
• scientific article; zbMATH DE number 1843075
• Variational inference for Dirichlet process mixtures
• scientific article; zbMATH DE number 802696

Cites work

• scientific article; zbMATH DE number 3673370 (Why is no real title available?)
• Dimensionally reduced model-based clustering through mixtures of factor mixture analyzers
• Finite mixture models
• Heteroscedastic factor mixture analysis
• Methods for merging Gaussian mixture components
• Model-Based Clustering, Discriminant Analysis, and Density Estimation
• Modelling high-dimensional data by mixtures of factor analyzers

Cited in

(14)

• Mixed Deep Gaussian Mixture Model: a clustering model for mixed datasets
• How deep are deep Gaussian processes?
• Leveraging Weather Dynamics in Insurance Claims Triage Using Deep Learning
• Latent Gaussian random field mixture models
• Mixture of experts distributional regression: implementation using robust estimation with adaptive first-order methods
• A Festschrift for Geoff McLachlan
• Deep multiscale model learning
• deepgmm
• Better than the best? Answers via model ensemble in density-based clustering
• Deep mixtures of unigrams for uncovering topics in textual data
• Variational inference and sparsity in high-dimensional deep Gaussian mixture models
• Solving inverse problems using data-driven models
• Alpha-divergence minimization for deep Gaussian processes
• scientific article; zbMATH DE number 1843059 (Why is no real title available?)

Describes a project that uses

Uses Software

• DeepFace
• mclust

This page was built for publication: Deep Gaussian mixture models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q88400)