Tau lepton identification and reconstruction: a new frontier for jet-tagging ML algorithms

Abstract

Identifying and reconstructing hadronic $\tau$ decays (${\tau }_{\text{h}}$) is an important task at current and future high-energy physics experiments, as ${\tau }_{\text{h}}$ represent an important tool to analyze the production of Higgs and electroweak bosons as well as to search for physics beyond the Standard Model. The identification of ${\tau }_{\text{h}}$ can be viewed as a generalization and extension of jet-flavour tagging, which has in the recent years undergone significant progress due to the use of deep learning. Based on a granular simulation with realistic detector effects and a particle flow-based event reconstruction, we show in this paper that deep learning-based jet-flavour-tagging algorithms are powerful ${\tau }_{\text{h}}$ identifiers. Specifically, we show that jet-flavour-tagging algorithms such as LorentzNet and ParticleTransformer can be adapted in an end-to-end fashion for discriminating ${\tau }_{\text{h}}$ from quark and gluon jets. We find that the end-to-end transformer-based approach significantly outperforms contemporary state-of-the-art ${\tau }_{\text{h}}$ reconstruction and identification algorithms currently in use at the Large Hadron Collider.

arXiv comment22 pages, 7 figures

References in corpus (18)

• Scikit-learn: Machine Learning in Python
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• ParticleNet: Jet Tagging via Particle Clouds
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Flavor Violating Higgs Decays
• Jet Substructure at the Large Hadron Collider: Experimental Review
• Evidence for the Higgs-boson Yukawa coupling to tau leptons with the ATLAS detector
• A New Mass Reconstruction Technique for Resonances Decaying to di-tau
• Higgs Physics at the CLIC Electron-Positron Linear Collider
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• The Pandora Software Development Kit for Pattern Recognition
• Performance of Particle Flow Calorimetry at CLIC
• Search for the direct production of charginos and neutralinos in $\sqrt{s}$ = 13 TeV $pp$ collisions with the ATLAS detector
• Jet reconstruction at high-energy lepton colliders
• Identification of hadronic tau lepton decays using a deep neural network
• Search for direct pair production of supersymmetric partners to the $\tau$ lepton in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Reconstruction of the Higgs mass in events with Higgs bosons decaying into a pair of tau leptons using matrix element techniques
• Luminosity determination using Z boson production at the CMS experiment

Cited by in corpus (3)

• Lepton Flavor Violation: From Muon Decays to Muon Colliders
• A unified machine learning approach for reconstructing hadronically decaying tau leptons
• Reconstructing hadronically decaying tau leptons with a jet foundation model