Optimal oracle inequalities for model selection
Statistics Theory
2008-12-18 v1 Statistics Theory
Abstract
Model selection is often performed by empirical risk minimization. The quality of selection in a given situation can be assessed by risk bounds, which require assumptions both on the margin and the tails of the losses used. Starting with examples from the 3 basic estimation problems, regression, classification and density estimation, we formulate risk bounds for empirical risk minimization under successively weakening conditions and prove them at a very general level, for general margin and power tail behavior of the excess losses.
Cite
@article{arxiv.0806.4140,
title = {Optimal oracle inequalities for model selection},
author = {Charles Mitchell and Sara van de Geer},
journal= {arXiv preprint arXiv:0806.4140},
year = {2008}
}
Comments
Submitted to the Electronic Journal of Statistics (http://www.i-journals.org/ejs/) by the Institute of Mathematical Statistics (http://www.imstat.org)