BOOST 2021 : 13th International Workshop on Boosted Object Phenomenology, Reconstruction and Searches in HEP

Session

ML : Pileup Mitigation + Jet Tagging

ML

2 Aug 2021, 17:20

Online

Conveners

ML : Pileup Mitigation + Jet Tagging

• Teng Jian Khoo (Humboldt University of Berlin (DE))

41. Safely Eating Junk: Pileup and Infrared Radiation Annihilation

Samuel Alipour-fard

02/08/2021, 17:20

Jet grooming is an important tool for the analysis of relativistic particle collisions despite the presence of contaminating radiation. Modern jet grooming techniques, such as Soft Drop grooming, introduce sharp cutoffs to remove soft radiation. These sharp cutoffs can lead to discontinuous behavior and associated experimental and theoretical challenges. In this talk, I introduce a new class...

54. Semi-supervised machine learning for pileup per particle identification at the LHC with Graph Neural Networks

Yongbin Feng (Fermi National Accelerator Lab. (US))

02/08/2021, 17:35

The high instantaneous luminosity of the LHC leads to multiple proton-proton interactions in the same or nearby bunch crossings (pileup). With the planned increasing instantaneous luminosity in the LHC's future runs, precise identification of individual particles produced from the hard scattering against pileup becomes crucial as this can significantly improve the performance of many physics...

95. Jet tagging in the Lund plane with graph networks

Frederic Alexandre Dreyer (University of Oxford)

02/08/2021, 17:50

The identification of boosted heavy particles such as top quarks or vector bosons is one of the key problems arising in experimental studies at the Large Hadron Collider. In this talk, we present LundNet, a novel jet tagging method which relies on graph neural networks and an efficient description of the radiation patterns within a jet to optimally disentangle signatures of boosted objects...