On EM Estimation for Mixture of Multivariate t-Distributions

Authors:
Haixian Wang;Zilan Hu
Affiliations:
Key Laboratory of Child Development and Learning Science of Ministry of Education, Research Center for Learning Science, Southeast University, Nanjing, People's Republic of China 210096;School of Mathematics and Physics, Anhui University of Technology, Maanshan, People's Republic of China 243002
Venue:
Neural Processing Letters
Year:
2009

Citing 18
Cited 3

Statistical Pattern Recognition: A Review

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust mixture modelling using the t distribution

Statistics and Computing
Mixture model clustering for mixed data with missing information

Computational Statistics & Data Analysis
Bayesian analysis of mixture modelling using the multivariate t distribution

Statistics and Computing
Robust mixture modelling using multivariate t-distribution with missing information

Pattern Recognition Letters
Feature representation and discrimination based on Gaussian mixture model probability densities-Practices and algorithms

Pattern Recognition
Missing data imputation through GTM as a mixture of t-distributions

Neural Networks
Handling of incomplete data sets using ICA and SOM in data mining

Neural Computing and Applications
Imputation through finite Gaussian mixture models

Computational Statistics & Data Analysis
Extension of the mixture of factor analyzers model to incorporate the multivariate t-distribution

Computational Statistics & Data Analysis
On Classification with Incomplete Data

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Semi-supervised Learning Algorithm on Gaussian Mixture with Automatic Model Selection

Neural Processing Letters
A particular Gaussian mixture model for clustering and its application to image retrieval

Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special issue on neural networks for pattern recognition and data mining
A finite mixture model for image segmentation

Statistics and Computing
Multinomial mixture model with feature selection for text clustering

Knowledge-Based Systems
Probabilistic two-dimensional principal component analysis and its mixture model for face recognition

Neural Computing and Applications
Mixture-model cluster analysis using information theoretical criteria

Intelligent Data Analysis
Robust speaker identification based on t-distribution mixture model

AI'05 Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence

Probabilistic self-organizing maps for continuous data

IEEE Transactions on Neural Networks
The infinite Student's t-mixture for robust modeling

Signal Processing
Learning from incomplete data via parameterized t mixture models through eigenvalue decomposition

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper formulates a novel expectation maximization (EM) algorithm for the mixture of multivariate t-distributions. By introducing a new kind of "missing" data, we show that the empirically improved iterative algorithm, in literature, for the mixture of multivariate t-distributions is in fact a type of EM algorithm; thus a theoretical analysis is established, which guarantees the empirical algorithm converges to the maximization likelihood estimates of the mixture parameters. Simulated experiment and real experiments on classification and image segmentation confirm the effectiveness of the improved EM algorithm.