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

CMS Collaboration

Research output: Contribution to journalArticleResearchpeer-review

66 Citations (Scopus)


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 = 13TeV, corresponding to an integrated luminosity of 35.9 fb-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.

Original languageEnglish
Article numberP06005
Number of pages87
JournalJournal of Instrumentation
Issue number6
Publication statusPublished - 3 Jun 2020


  • Large detector-systems performance
  • Pattern recognition, cluster finding, calibration and fitting methods

Cite this