Identification of hadronic tau lepton decays using a deep neural network

A new algorithm is presented to discriminate reconstructed hadronic decays of tau leptons (tau(h)) that originate from genuine tau leptons in the CMS detector against tau(h) candidates that originate from quark or gluon jets, electrons, or muons. The algorithm inputs information from all reconstructed particles in the vicinity of a tau(h) candidate and employs a deep neural network with convolutional layers to efficiently process the inputs. This algorithm leads to a significantly improved performance compared with the previously used one. For example, the efficiency for a genuine tau(h) to pass the discriminator against jets increases by 10-30% for a given efficiency for quark and gluon jets. Furthermore, a more efficient tau(h) reconstruction is introduced that incorporates additional hadronic decay modes. The superior performance of the new algorithm to discriminate against jets, electrons, and muons and the improved tau(h) reconstruction method are validated with LHC proton-proton collision data at root s = 13 TeV.

Automated summary

This paper presents a new algorithm to discriminate reconstructed hadronic decays of tau leptons and candidates from other particles in the CMS detector. The algorithm utilizes a deep neural network with convolutional layers to process input data efficiently and achieves significantly improved performance compared to the previous algorithm. Additionally, a more efficient reconstruction method for hadronic decay modes is introduced.