Exact and empirical estimation of misclassification probability
Machine Learning
2014-08-15 v1 Machine Learning
Abstract
We discuss the problem of risk estimation in the classification problem, with specific focus on finding distributions that maximize the confidence intervals of risk estimation. We derived simple analytic approximations for the maximum bias of empirical risk for histogram classifier. We carry out a detailed study on using these analytic estimates for empirical estimation of risk.
Cite
@article{arxiv.1408.3332,
title = {Exact and empirical estimation of misclassification probability},
author = {Victor Nedelko},
journal= {arXiv preprint arXiv:1408.3332},
year = {2014}
}