Deep learning jet substructure from two-particle correlations

Abstract

Deciphering the complex information contained in jets produced in collider events requires a physical organization of the jet data. We introduce two-particle correlations (2PCs) by pairing individual particles as the initial jet representation from which a probabilistic model can be built. Particle momenta as well as particle types and vertex information are included in the correlation. A novel, two-particle correlation neural network (2PCNN) architecture is constructed by combining neural-network-based filters on 2PCs and a deep neural network for capturing jet kinematic information. The 2PCNN is applied to boosted boson and heavy flavor tagging, and it achieves excellent performance by comparing to image-based convolutional neural network and telescoping deconstruction. Major correlation pairs exploited in the trained models are also identified, which shed light on the physical significance of certain jet substructure.