Maximum Regularized Likelihood Estimators: A General Prediction Theory and Applications
Machine Learning
2018-10-18 v2 Statistics Theory
Statistics Theory
Abstract
Maximum regularized likelihood estimators (MRLEs) are arguably the most established class of estimators in high-dimensional statistics. In this paper, we derive guarantees for MRLEs in Kullback-Leibler divergence, a general measure of prediction accuracy. We assume only that the densities have a convex parametrization and that the regularization is definite and positive homogenous. The results thus apply to a very large variety of models and estimators, such as tensor regression and graphical models with convex and non-convex regularized methods. A main conclusion is that MRLEs are broadly consistent in prediction - regardless of whether restricted eigenvalues or similar conditions hold.
Cite
@article{arxiv.1710.02950,
title = {Maximum Regularized Likelihood Estimators: A General Prediction Theory and Applications},
author = {Rui Zhuang and Johannes Lederer},
journal= {arXiv preprint arXiv:1710.02950},
year = {2018}
}