English

Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques

High Energy Physics - Experiment 2020-06-09 v2 Instrumentation and Detectors

Abstract

Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at s=\sqrt{s} = 13 TeV, corresponding to an integrated luminosity of 35.9 fb1^{-1}. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.

Keywords

Cite

@article{arxiv.2004.08262,
  title  = {Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques},
  author = {CMS Collaboration},
  journal= {arXiv preprint arXiv:2004.08262},
  year   = {2020}
}

Comments

Replaced with the published version. Added the journal reference and the DOI. All the figures and tables can be found at http://cms-results.web.cern.ch/cms-results/public-results/publications/JME-18-002 (CMS Public Pages)

R2 v1 2026-06-23T14:55:19.440Z