End-to-End Jet Classification of Boosted Top Quarks with the CMS Open Data
This work addresses jet classification in high-energy physics for researchers, but it is incremental as it applies an existing end-to-end method to new data with performance benchmarks.
The paper tackled the problem of discriminating top quark-initiated jets from light quark or gluon jets using end-to-end deep learning on CMS Open Data, achieving an AUC score of 0.975 with calorimeter and pixel data and improving to 0.9824 with additional tracking information.
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.