Speaker
Description
A novel deep neural network classifier, the “particle transformer” (ParT), is introduced for the identification of highly Lorentz-boosted, multi-pronged jets in measurements and searches performed with the CMS detector at the LHC. Based on a self-attention mechanism that allows the model to weigh the importance of different particles, ParT is trained on a wide variety of topologies, notably demonstrating strong performance for the first time on jets originating from boosted Higgs boson decays to W bosons. The ParT algorithm achieves a tagging efficiency of >50% for such jets at a QCD multijet background efficiency of 1%, while maintaining decorrelation from the jet mass. This performance is calibrated in data collected by CMS from proton-proton collisions at 13 TeV center-of-mass energy, with a dataset corresponding to a total luminosity of 138 fb^-1, using the primary Lund jet planes of individual subjets. Data-to-simulation selection efficiency scale factors are measured to be in the 0.9–1 range, with relative uncertainties ranging between 7 and 23%.
