Classification with the matrix-variate-$t$ distribution
Methodology
2019-12-24 v2 Applications
Computation
Machine Learning
Abstract
Matrix-variate distributions can intuitively model the dependence structure of matrix-valued observations that arise in applications with multivariate time series, spatio-temporal or repeated measures. This paper develops an Expectation-Maximization algorithm for discriminant analysis and classification with matrix-variate -distributions. The methodology shows promise on simulated datasets or when applied to the forensic matching of fractured surfaces or the classification of functional Magnetic Resonance, satellite or hand gestures images.
Cite
@article{arxiv.1907.09565,
title = {Classification with the matrix-variate-$t$ distribution},
author = {Geoffrey Z. Thompson and Ranjan Maitra and William Q. Meeker and Ashraf Bastawros},
journal= {arXiv preprint arXiv:1907.09565},
year = {2019}
}
Comments
12 pages, 7 figures