Convex Geometry of the Generalized Matrix-Fractional Function
Optimization and Control
2017-03-07 v1 Machine Learning
Machine Learning
Abstract
Generalized matrix-fractional (GMF) functions are a class of matrix support functions introduced by Burke and Hoheisel as a tool for unifying a range of seemingly divergent matrix optimization problems associated with inverse problems, regularization and learning. In this paper we dramatically simplify the support function representation for GMF functions as well as the representation of their subdifferentials. These new representations allow the ready computation of a range of important related geometric objects whose formulations were previously unavailable.
Cite
@article{arxiv.1703.01363,
title = {Convex Geometry of the Generalized Matrix-Fractional Function},
author = {James V. Burke and Yuan Gao and Tim Hoheisel},
journal= {arXiv preprint arXiv:1703.01363},
year = {2017}
}