Abstract
Hadronic decays of vector bosons and top quarks are increasingly important to the ATLAS physics program, both in measurements of the Standard Model and searches for new physics. At high energies, these decays are collimated into a single overlapping region of energy deposits in the detector, referred to as a jet. However, vector bosons and top quarks are hidden under an enormous background of other processes producing jets. The ATLAS experiment has employed boosted decision trees and deep neural networks to the challenging task of identifying hadronically-decaying vector bosons and top quarks and rejecting other jet backgrounds. These discriminants are becoming increasingly complex and using more advanced machine learning techniques. The methods currently used to tag these objects are described. In order to improve the tagger performance on the signal efficiency and background rejection, new in-situ techniques are applied, thus directly evaluating the agreement between data and simulation after applying an arbitrarily complex classifier. The precision obtained by applying the in-situ techniques is presented.
Highlights
The high centre-of-mass energy of 13 TeV at the Large Hadron Collider (LHC) [1] in Run 2 allows the physics programme at the ATLAS experiment [2] to probe processes with highly boosted massive decaying particles in the final state, such as vector bosons and top quarks
The two background topologies differ in terms of the contribution of quark-induced and gluon-induced jets, and the γ+jet allows to study the background rejection modelling at lower jet pT due to the lower photon trigger threshold compared to the single-jet trigger
Advanced methods for identification of boosted hadronically-decaying top quarks and W bosons using boosted decision trees (BDTs) and deep neural networks (DNNs) by combining multiple high-level features, or using low-level information from jet clusters are examined by ATLAS
Summary
The high centre-of-mass energy of 13 TeV at the Large Hadron Collider (LHC) [1] in Run 2 allows the physics programme at the ATLAS experiment [2] to probe processes with highly boosted massive decaying particles in the final state, such as vector bosons and top quarks. Optimisation of the ML algorithms using high-level features Two approaches of combining high-level features are examined – boosted decision trees (BDTs) and DNNs, with the goal to determine if one of the ML algorithms is better suited to exploit the differences of the features and their correlations for signal and background jets Both ML techniques are trained on jets with mass m > 40 GeV and at least three constituents. The difference in performance between ML-based taggers and simpler taggers is much larger for top-tagging as opposed to W -boson tagging This can be attributed to the richer structure of the top decay leading to more distinct features in contrast to jets from multijet background
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
