New approaches for boosting to uniformity
High Energy Physics - Experiment
2015-06-23 v1
Abstract
The use of multivariate classifiers has become commonplace in particle physics. To enhance the performance, a series of classifiers is typically trained; this is a technique known as boosting. This paper explores several novel boosting methods that have been designed to produce a uniform selection efficiency in a chosen multivariate space. Such algorithms have a wide range of applications in particle physics, from producing uniform signal selection efficiency across a Dalitz-plot to avoiding the creation of false signal peaks in an invariant mass distribution when searching for new particles.
Cite
@article{arxiv.1410.4140,
title = {New approaches for boosting to uniformity},
author = {Alex Rogozhnikov and Aleksandar Bukva and Vladimir Gligorov and Andrey Ustyuzhanin and Mike Williams},
journal= {arXiv preprint arXiv:1410.4140},
year = {2015}
}