Complexity Regularization and Local Metric Entropy
Statistics Theory
2016-09-12 v1 Statistics Theory
Abstract
In the context of Structural Risk Minimization, one is presented a sequence of classes from which, given a random sample one wants to choose a strongly consistent estimator. For certain types of classes of functions, we present a criterion to choose an estimator, based on the minimization of the sum of empirical error and a complexity penalty over each class . We present also several other results together with important results found on current literature on the subject, in an attempt to present and unify the theory in the context of regression estimation. In particular we present a generalization of the consistency of Structural Risk Minimization in the context of regression estimation which are all new results found on Chapter 5.
Cite
@article{arxiv.1609.02855,
title = {Complexity Regularization and Local Metric Entropy},
author = {Fabián Latorre},
journal= {arXiv preprint arXiv:1609.02855},
year = {2016}
}