The Machine Learning Landscape of Top Taggers

Abstract

Based on the established task of identifying boosted, hadronically decaying top quarks, we compare a wide range of modern machine learning approaches. Unlike most established methods they rely on low-level input, for instance calorimeter output. While their network architectures are vastly different, their performance is comparatively similar. In general, we find that these new approaches are extremely powerful and great fun.

Figure 5: ROC curves for each of the models compared in this paper. Some models, including the PFN and EFN (which used the hyperparameters of a quark/gluon jet tagger), were not optimized for top tagging.