Exploring the Universality of Hadronic Jet Classification
This addresses the challenge of simulation discrepancies in particle physics for researchers at facilities like the LHC, though it is incremental as it builds on existing classification methods.
The study found that machine learning classifiers for jet substructure achieve nearly identical performance when trained on different simulation programs, indicating that models trained on one simulation are likely optimal for others or real data.
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.