End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data
High Energy Physics - Experiment
2020-10-27 v2 Computer Vision and Pattern Recognition
Machine Learning
Data Analysis, Statistics and Probability
Abstract
We describe the construction of end-to-end jet image classifiers based on simulated low-level detector data to discriminate quark- vs. gluon-initiated jets with high-fidelity simulated CMS Open Data. We highlight the importance of precise spatial information and demonstrate competitive performance to existing state-of-the-art jet classifiers. We further generalize the end-to-end approach to event-level classification of quark vs. gluon di-jet QCD events. We compare the fully end-to-end approach to using hand-engineered features and demonstrate that the end-to-end algorithm is robust against the effects of underlying event and pile-up.
Keywords
Cite
@article{arxiv.1902.08276,
title = {End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data},
author = {Michael Andrews and John Alison and Sitong An and Patrick Bryant and Bjorn Burkle and Sergei Gleyzer and Meenakshi Narain and Manfred Paulini and Barnabas Poczos and Emanuele Usai},
journal= {arXiv preprint arXiv:1902.08276},
year = {2020}
}
Comments
10 pages, 5 figures, 7 tables; v2: published version