https://doi.org/10.1140/epjc/s10052-020-7608-4
Regular Article - Experimental Physics
JEDI-net: a jet identification algorithm based on interaction networks
1
California Institute of Technology, Pasadena, CA, 91125, USA
2
Fermi National Accelerator Laboratory (FNAL), Batavia, IL, 60510, USA
3
University of California San Diego, La Jolla, CA, 92093, USA
4
European Center for Nuclear Research (CERN), 1211, Geneva, Switzerland
* e-mail: javier.mauricio.duarte@cern.ch
Received:
10
September
2019
Accepted:
3
January
2020
Published online:
25
January
2020
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.
© The Author(s), 2020
