Multithreshold Entropy Linear Classifier (MELC) is a recent classifier idea which employs information theoretic concept in order to create a multithreshold maximum margin model. In this paper we analyze its consistency over multithreshold linear models and show that its objective function upper bounds the amount of misclassified points in a similar manner like hinge loss does in support vector machines. For further confirmation we also conduct some numerical experiments on five datasets.
@article{arxiv.1504.04740,
title = {On the consistency of Multithreshold Entropy Linear Classifier},
author = {Wojciech Marian Czarnecki},
journal= {arXiv preprint arXiv:1504.04740},
year = {2015}
}
Comments
Presented at Theoretical Foundations of Machine Learning 2015 (http://tfml.gmum.net), final version published in Schedae Informaticae Journal