Exploring the Universality of Hadronic Jet Classification
arXiv:2204.03812 · doi:10.1140/epjc/s10052-022-11084-4
Abstract
The modeling of jet substructure significantly differs between Parton Shower Monte Carlo (PSMC) programs. Despite this, we observe that machine learning classifiers trained on different PSMCs learn nearly the same function. This means that when these classifiers are applied to the same PSMC for testing, they result in nearly the same performance. This classifier universality indicates that a machine learning model trained on one simulation and tested on another simulation (or data) will likely be optimal. Our observations are based on detailed studies of shallow and deep neural networks applied to simulated Lorentz boosted Higgs jet tagging at the LHC.
25 pages, 7 figures, 7 tables
References in corpus (7)
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
- The Catchment Area of Jets
- Power Counting to Better Jet Observables
- Uncertainty Aware Learning for High Energy Physics
- Multipole Photon Radiation in the Vincia Parton Shower
- Efficient multi-jet merging with the Vincia sector shower
- Taming modeling uncertainties with Mass Unspecific Supervised Tagging