MSci Project

Identification of Hadronic Tau Lepton Decays with Domain Adaptation using Adversarial Machine Learning Techniques at CMS

November 2021-July 2022

My MSci project was on the identification of hadronic tau lepton decays at the Compact Muon Solenoid experiment, using a deep convolutional neural network called DeepTau. I introduced domain adaptation into the training workflow using adversarial machine learning techniques, which significantly reduced performance discrepancies between collider data and simulated events for discrimination against quark and gluon jets. This work has been integrated into central CMS software and will be used for physics analyses of the early Run 3 data taking period.

My thesis is available online at cds.cern.ch/record/2827366/, you can read the abstract here:

This thesis reports improved machine learning-based techniques to discriminate genuine decays of tau leptons into hadrons and a neutrino against all main backgrounds at the CMS experiment. The deep convolutional neural network, DeepTau, used for tau identification by physics analyses of the 2016-2018 data-taking period at CMS, shows a sizeably different performance on collider data versus Monte Carlo simulations. This effect is particularly prominent for regions of parameter space that have high genuine tau purity. The effects of this mismodelling on discrimination against quark and gluon jets are reduced by introducing domain adaptation into the training workflow. This approach was validated by comparing the performance of the resulting network on proton-proton collision data and simulated events. The use of these adversarial machine learning techniques reduced the discrepancies from 13.3% to 0.80% in the region where the purity of hadronic taus is expected to be above 96%, while having no significant impact on tau identification performance.