Machine Learning Study on Single Production of a Singlet Vector-like Lepton at the Large Hadron Collider

TL;DR

This study uses machine learning to improve the detection prospects of single production of a singlet vector-like lepton at the LHC, achieving significant mass exclusion limits.

Contribution

It introduces a novel application of XGBoost to enhance signal-background discrimination in vector-like lepton searches at the LHC.

Findings

2σ exclusion limits up to 620 GeV for three-lepton channel

490 GeV for four-lepton channel

Machine learning significantly improves search sensitivity

Abstract

Vector-like leptons are non-chiral, colorless fermions from new physics beyond the Standard Model, appearing in many theoretical extensions. We investigate the prospect for detecting the single production of a singlet vector-like lepton that mixes with the $\tau$ lepton at the Large Hadron Collider. The corresponding final states are classified as the three- and four-lepton search channels. The machine learning algorithm XGBoost is employed to enhance signal-background discrimination. Our analysis indicates that, at $\sqrt{s} = 14~\mathrm{TeV}$ with an integrated luminosity of $3000~\mathrm{fb}^{-1}$, the expected $2\sigma$ exclusion limits in the three- and four-lepton channels can reach vector-like lepton masses up to $620~\mathrm{GeV}$ and $490~\mathrm{GeV}$, respectively. These findings demonstrate that machine learning techniques can substantially improve the sensitivity of collider searches for vector-like leptons.