9-12 February 2021
Virtual Meeting
America/Toronto timezone

Search for New Physics Inside Jets at the ATLAS Detector Using Machine Learning

12 Feb 2021, 12:45
Virtual Meeting

Virtual Meeting

Physics Beyond the Standard Model


Mrs Jacinthe Pilette (Université de Montréal)


Since the discovery of the Higgs Boson at the LHC in 2012, no sign of new physics beyond the Standard Model has been found. The SUSY and exotic particles searches have not uncovered signs of new physics, as the model-dependent searches. In recent years, multiple unsupervised machine learning methods have been proposed to search for new physics at the LHC. This talk will explore the use of a variational auto-encoder (VAE) to perform a general search in proton-proton collisions at the LHC using large radius jets in ATLAS simulation data. The algorithm was trained on TopoClusters to differentiate between the dominant QCD background and a chosen test signal corresponding to top quark jets. The most anomalous jets predicted by the VAE were selected to plot the invariant mass spectrum to find the top quark mass peak. Our study found an important correlation between the jet invariant mass and the loss function of the VAE, resulting in QCD background sculpting and preventing the apparition of the top peak. We successfully used a mass-decorrelation method based on Outlier Exposure to prevent this sculpting.

email address jacinthe.pilette@umontreal.ca
Please select: Experiment or Theory Experiment

Primary author

Mrs Jacinthe Pilette (Université de Montréal)


Mr Dominique Godin (Université de Montréal) Mr Jean-François Arguin (Université de Montréal) Mr Julien Leissner-Martin (Université de Montréal) Mrs Taoli Cheng (MILA)

Presentation Materials

Your browser is out of date!

Update your browser to view this website correctly. Update my browser now