Ridge Fusion in Statistical Learning
Machine Learning
2014-05-06 v3 Machine Learning
Computation
Abstract
We propose a penalized likelihood method to jointly estimate multiple precision matrices for use in quadratic discriminant analysis and model based clustering. A ridge penalty and a ridge fusion penalty are used to introduce shrinkage and promote similarity between precision matrix estimates. Block-wise coordinate descent is used for optimization, and validation likelihood is used for tuning parameter selection. Our method is applied in quadratic discriminant analysis and semi-supervised model based clustering.
Cite
@article{arxiv.1310.3892,
title = {Ridge Fusion in Statistical Learning},
author = {Bradley S. Price and Charles J. Geyer and Adam J. Rothman},
journal= {arXiv preprint arXiv:1310.3892},
year = {2014}
}
Comments
24 pages and 9 tables, 3 figures