JEDI-net: a jet identification algorithm based on interaction networks
Eric Moreno (California Institute of Technology, Pasadena, CA, 91125, USA); Olmo Cerri (California Institute of Technology, Pasadena, CA, 91125, USA); Javier Duarte (Fermi National Accelerator Laboratory (FNAL), Batavia, IL, 60510, USA, University of California San Diego, La Jolla, CA, 92093, USA); Harvey Newman (California Institute of Technology, Pasadena, CA, 91125, USA); Thong Nguyen (California Institute of Technology, Pasadena, CA, 91125, USA); et al - Show all 10 authors
We investigate the performance of a jet identification algorithm based on interaction networks (JEDI-net) to identify all-hadronic decays of high-momentum heavy particles produced at the LHC and distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The jet dynamics are described as a set of one-to-one interactions between the jet constituents. Based on a representation learned from these interactions, the jet is associated to one of the considered categories. Unlike other architectures, the JEDI-net models achieve their performance without special handling of the sparse input jet representation, extensive pre-processing, particle ordering, or specific assumptions regarding the underlying detector geometry. The presented models give better results with less model parameters, offering interesting prospects for LHC applications.
