End-to-End Jet Classification of Boosted Top Quarks with the CMS Open Data

TL;DR

This paper applies end-to-end deep learning to classify boosted top quark jets using CMS Open Data, demonstrating high accuracy and the benefit of tracking information, and provides a performance benchmark for these data samples.

Contribution

It introduces a novel end-to-end deep learning approach for jet classification using CMS Open Data, incorporating low-level detector information and benchmarking performance.

Findings

Achieved an AUC of 0.975 using calorimeter data

Improved AUC to 0.9824 with additional tracking information

Provided the first performance benchmark for CMS Open Data samples

Abstract

We describe a novel application of the end-to-end deep learning technique to the task of discriminating top quark-initiated jets from those originating from the hadronization of a light quark or a gluon. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation of the high-energy collision event. In this study, we use low-level detector information from the simulated CMS Open Data samples to construct the top jet classifiers. To optimize classifier performance we progressively add low-level information from the CMS tracking detector, including pixel detector reconstructed hits and impact parameters, and demonstrate the value of additional tracking information even when no new spatial structures are added. Relying only on calorimeter energy deposits and reconstructed pixel detector hits, the end-to-end classifier achieves an AUC score of 0.975$\pm$0.002 for the task of classifying boosted top quark jets. After adding derived track quantities, the classifier AUC score increases to 0.9824$\pm$0.0013, serving as the first performance benchmark for these CMS Open Data samples. We additionally provide a timing performance comparison of different processor unit architectures for training the network.