A deep neural network to search for new long-lived particles decaying to jets

• Published in: Machine learning: science and technology 2020-09, Vol.1 (3), p.35012
• Main Authors: Sirunyan, A. M., Tumasyan, A., Adam, W., Ambrogi, F., Bergauer, T.
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; CMS; Computer simulation; deep neural network; Jets; Large Hadron Collider; long-lived particles; Machine learning; Marking; Neural networks; Particle decay; PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; Protons; Solenoids; split SUSY; Supersymmetry
• ISSN: 2632-2153; 2632-2153
• DOI: 10.1088/2632-2153/ab9023

A tagging algorithm to identify jets that are significantly displaced from the proton-proton (pp) collision region in the CMS detector at the LHC is presented. Displaced jets can arise from the decays of long-lived particles (LLPs), which are predicted by several theoretical extensions of the standard model. The tagger is a multiclass classifier based on a deep neural network, which is parameterised according to the proper decay length cτ0 of the LLP. A novel scheme is defined to reliably label jets from LLP decays for supervised learning. Samples of pp collision data, recorded by the CMS detector at a centre-of-mass energy of 13 TeV, and simulated events are used to train the neural network. Domain adaptation by backward propagation is performed to improve the simulation modelling of the jet class probability distributions observed in pp collision data. The potential performance of the tagger is demonstrated with a search for long-lived gluinos, a manifestation of split supersymmetric models. The tagger provides a rejection factor of 10 000 for jets from standard model processes, while maintaining an LLP jet tagging efficiency of 30%-80% for gluinos with 1 mm≤cτ0≤ 10 m. The expected coverage of the parameter space for split supersymmetry is presented.