Open Collections

UBC Faculty Research and Publications

A Bootstrap-augmented AECM Algorithm for Mixtures of Factor Analyzers Shreeves, Phillip; Andrews, Jeffrey L.

Abstract

Finite mixture models are a popular approach for unsupervised machine learning tasks. Mixtures of factor analyzers assume a latent variable structure, thereby modelling the data in a lower-dimensional space. Herein, we augment the traditional alternating expectation conditional maximization algorithm by incorporating the non-parametric bootstrap during the parameter estimation process. This augmentation is shown to improve discovery of both the true number of groups and the true latent dimensionality through simulations, while also showing superior clustering performance on benchmark data sets.

Item Metadata

Title
A Bootstrap-augmented AECM Algorithm for Mixtures of Factor Analyzers
Creator
Shreeves, Phillip; Andrews, Jeffrey L.
Date Issued
2019-08-21
Description
Finite mixture models are a popular approach for unsupervised machine learning tasks. Mixtures of factor analyzers assume a latent variable structure, thereby modelling the data in a lower-dimensional space. Herein, we augment the traditional alternating expectation conditional maximization algorithm by incorporating the non-parametric bootstrap during the parameter estimation process. This augmentation is shown to improve discovery of both the true number of groups and the true latent dimensionality through simulations, while also showing superior clustering performance on benchmark data sets.
Subject
Cluster analysis; Mixture models; Factor analysis; Bootstrap; EM algorithm
Genre
Article; Postprint
Type
Text
Language
eng
Date Available
2025-03-05
Provider
Vancouver : University of British Columbia Library
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
DOI
10.14288/1.0448167
URI
http://hdl.handle.net/2429/90460
Affiliation
Science, Irving K. Barber Faculty of (Okanagan); Computer Science, Mathematics, Physics and Statistics, Department of (Okanagan)
Citation
Shreeves, P., & Andrews, J. L. (2019). A bootstrap-augmented alternating expectation‐conditional maximization algorithm for mixtures of factor analyzers. Stat, 8(1), e243
Publisher DOI
10.1002/sta4.243
Peer Review Status
Reviewed
Scholarly Level
Faculty; Graduate
Rights URI
http://creativecommons.org/licenses/by-nc-nd/4.0/
Aggregated Source Repository
DSpace

Item Media

Item Citations and Data

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International