ADAM J. ROTHMAN
School of Statistics
University of Minnesota
“Bridge Penalized Gaussian Likelihood Precision Matrix Estimation and Applications”
ABSTRACT
We establish a necessary and sufficient condition for the existence of the precision matrix estimate obtained by minimizing the negative Gaussian log-likelihood plus a weighted Bridge penalty. This condition enables us to connect the literature on Gaussian graphical models to the literature on penalized Gaussian likelihood. We also discuss applications of this estimator in multiple response regression and classification.
