Machine learning classification: case of Higgs boson CP state in H to tau tau decay at LHC

Abstract

Machine Learning (ML) techniques are rapidly finding a place among the methods of High Energy Physics data analysis. Different approaches are explored concerning how much effort should be put into building high-level variables based on physics insight into the problem, and when it is enough to rely on low-level ones, allowing ML methods to find patterns without explicit physics model. In this paper we continue the discussion of previous publications on the CP state of the Higgs boson measurement of the H to tau tau decay channel with the consecutive tau^pm to rho^pm nu; rho^pm to pi^pm pi^0 and tau^pm to a_1^pm nu; a_1^pm to rho^0 pi^pm to 3 pi^pm cascade decays. The discrimination of the Higgs boson CP state is studied as a binary classification problem between CP-even (scalar) and CP-odd (pseudoscalar), using Deep Neural Network (DNN). Improvements on the classification from the constraints on directly non-measurable outgoing neutrinos are discussed. We find, that once added, they enhance the sensitivity sizably, even if only imperfect information is provided. In addition to DNN we also evaluate and compare other ML methods: Boosted Trees (BT), Random Forest (RF) and Support Vector Machine (SVN).

arXiv comment1+20 pages, 9 figures, 6 tables, extended content and improved readability

References in corpus (41)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• An Introduction to PYTHIA 8.2
• Deep Learning using Rectified Linear Units (ReLU)
• Machine learning and the physical sciences
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• Performance of $b$-Jet Identification in the ATLAS Experiment
• Deep Learning and its Application to LHC Physics
• Evidence for the 125 GeV Higgs boson decaying to a pair of tau leptons
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• The Machine Learning Landscape of Top Taggers
• Parameterized Machine Learning for High-Energy Physics
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Performance of reconstruction and identification of $\tau$ leptons decaying to hadrons and ${\nu }_{\tau }$ in pp collisions at $\sqrt{s}=$ 13 TeV
• Universal Interface of TAUOLA Technical and Physics Documentation
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• Cross-section measurements of the Higgs boson decaying into a pair of tau-leptons in proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Prospects of Measuring the Parity of Higgs Particles
• QCD-Aware Recursive Neural Networks for Jet Physics
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Determining the CP parity of Higgs bosons at the LHC in the $\tau$ to 1-prong decay channels
• Reconstruction of hadronic decay products of tau leptons with the ATLAS experiment
• Measuring the Higgs boson's parity using tau --> rho nu
• Jet Charge and Machine Learning
• Probing the CP nature of the Higgs boson at linear colliders with tau spin correlations; the case of mixed scalar--pseudoscalar couplings
• Quark-Gluon Tagging: Machine Learning vs Detector
• Prospects of constraining the Higgs CP nature in the tau decay channel at the LHC
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Measuring the Higgs boson parity at a Linear Collider using the tau impact parameter and tau --> rho nu decay
• Potential for optimizing Higgs boson CP measurement in H to tau tau decay at LHC and ML techniques
• CP violation in a light Higgs boson decay from tau-spin correlations at a linear collider
• Tau Polarimetry with Multi Meson States
• Tau lepton reconstruction at collider experiments using impact parameters
• Deep learning approach to the Higgs boson CP measurement in H to tau tau decay and associated systematics
• TauSpinner: a tool for simulating CP effects in H to tau tau decays at LHC
• Support Vector Machines and generalisation in HEP
• Monte Carlo, fitting and Machine Learning for Tau leptons
• Kinematic reconstruction of $Z/H\to \tau \tau$ decay in proton-proton collisions
• A multi-instance deep neural network classifier: application to Higgs boson CP measurement

Cited by in corpus (5)

• Application of artificial intelligence in the determination of impact parameter in heavy-ion collisions at intermediate energies
• Measuring the anomalous quartic gauge couplings in the $W^{+}{W}^{-}\to W^{+}{W}^{-}$ process at muon collider using artificial neural networks
• Extract the energy scale of anomalous $\gamma \gamma \to W^{+}{W}^{-}$ scattering in the vector boson scattering process using artificial neural networks
• Deep Neural Network application: Higgs boson CP state mixing angle in H to tau tau decay and at LHC
• LHC Higgs CP Sensitive Observables in H to tau^+ tau^-; tau^pm to (3pi)^pm nu and Machine Learning Benefits