JEDI-net: a jet identification algorithm based on interaction networks
Abstract 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...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-01-01
|
| Series: | European Physical Journal C: Particles and Fields |
| Online Access: | https://doi.org/10.1140/epjc/s10052-020-7608-4 |
| _version_ | 1818665000103837696 |
|---|---|
| author | Eric A. Moreno Olmo Cerri Javier M. Duarte Harvey B. Newman Thong Q. Nguyen Avikar Periwal Maurizio Pierini Aidana Serikova Maria Spiropulu Jean-Roch Vlimant |
| author_facet | Eric A. Moreno Olmo Cerri Javier M. Duarte Harvey B. Newman Thong Q. Nguyen Avikar Periwal Maurizio Pierini Aidana Serikova Maria Spiropulu Jean-Roch Vlimant |
| author_sort | Eric A. Moreno |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-12-17T05:41:40Z |
| format | Article |
| id | doaj.art-2108a8d48c57476a9f436d012ca56ea6 |
| institution | Directory Open Access Journal |
| issn | 1434-6044 1434-6052 |
| language | English |
| last_indexed | 2024-12-17T05:41:40Z |
| publishDate | 2020-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Physical Journal C: Particles and Fields |
| spelling | doaj.art-2108a8d48c57476a9f436d012ca56ea62022-12-21T22:01:25ZengSpringerOpenEuropean Physical Journal C: Particles and Fields1434-60441434-60522020-01-0180111510.1140/epjc/s10052-020-7608-4JEDI-net: a jet identification algorithm based on interaction networksEric A. Moreno0Olmo Cerri1Javier M. Duarte2Harvey B. Newman3Thong Q. Nguyen4Avikar Periwal5Maurizio Pierini6Aidana Serikova7Maria Spiropulu8Jean-Roch Vlimant9California Institute of TechnologyCalifornia Institute of TechnologyFermi National Accelerator Laboratory (FNAL)California Institute of TechnologyCalifornia Institute of TechnologyCalifornia Institute of TechnologyEuropean Center for Nuclear Research (CERN)California Institute of TechnologyCalifornia Institute of TechnologyCalifornia Institute of TechnologyAbstract 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.https://doi.org/10.1140/epjc/s10052-020-7608-4 |
| spellingShingle | Eric A. Moreno Olmo Cerri Javier M. Duarte Harvey B. Newman Thong Q. Nguyen Avikar Periwal Maurizio Pierini Aidana Serikova Maria Spiropulu Jean-Roch Vlimant JEDI-net: a jet identification algorithm based on interaction networks European Physical Journal C: Particles and Fields |
| title | JEDI-net: a jet identification algorithm based on interaction networks |
| title_full | JEDI-net: a jet identification algorithm based on interaction networks |
| title_fullStr | JEDI-net: a jet identification algorithm based on interaction networks |
| title_full_unstemmed | JEDI-net: a jet identification algorithm based on interaction networks |
| title_short | JEDI-net: a jet identification algorithm based on interaction networks |
| title_sort | jedi net a jet identification algorithm based on interaction networks |
| url | https://doi.org/10.1140/epjc/s10052-020-7608-4 |
| work_keys_str_mv | AT ericamoreno jedinetajetidentificationalgorithmbasedoninteractionnetworks AT olmocerri jedinetajetidentificationalgorithmbasedoninteractionnetworks AT javiermduarte jedinetajetidentificationalgorithmbasedoninteractionnetworks AT harveybnewman jedinetajetidentificationalgorithmbasedoninteractionnetworks AT thongqnguyen jedinetajetidentificationalgorithmbasedoninteractionnetworks AT avikarperiwal jedinetajetidentificationalgorithmbasedoninteractionnetworks AT mauriziopierini jedinetajetidentificationalgorithmbasedoninteractionnetworks AT aidanaserikova jedinetajetidentificationalgorithmbasedoninteractionnetworks AT mariaspiropulu jedinetajetidentificationalgorithmbasedoninteractionnetworks AT jeanrochvlimant jedinetajetidentificationalgorithmbasedoninteractionnetworks |