Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network
arXiv:2311.08885 · doi:10.1088/2632-2153/ad611e
Abstract
The energy and mass measurements of jets are crucial tasks for the Large Hadron Collider experiments. This paper presents a new calibration method to simultaneously calibrate these quantities for large-radius jets measured with the ATLAS detector using a deep neural network (DNN). To address the specificities of the calibration problem, special loss functions and training procedures are employed, and a complex network architecture, which includes feature annotation and residual connection layers, is used. The DNN-based calibration is compared to the standard numerical approach in an extensive series of tests. The DNN approach is found to perform significantly better in almost all of the tests and over most of the relevant kinematic phase space. In particular, it consistently improves the energy and mass resolutions, with a 30% better energy resolution obtained for transverse momenta GeV.
50 pages in total, author list starting page 33, 14 figures, 3 tables, published as Mach. Learn. Sci. Technol. 5 035051 (2024). All figures including auxiliary figures are available at https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PAPERS/JETM-2023-02/
References in corpus (11)
- An Introduction to PYTHIA 8.2
- A parton shower algorithm based on Catani-Seymour dipole factorisation
- On the Variance of the Adaptive Learning Rate and Beyond
- Jet energy scale and resolution measured in proton-proton collisions at TeV with the ATLAS detector
- Strategies to Identify Boosted Tops
- Power Counting to Better Jet Observables
- 50 Years of Quantum Chromodynamics
- Progress measures for grokking via mechanistic interpretability
- Optimisation of large-radius jet reconstruction for the ATLAS detector in 13 TeV proton-proton collisions
- Parametrizing the Detector Response with Neural Networks
- New techniques for jet calibration with the ATLAS detector