Determination of the CMSSM Parameters using Neural Networks

Abstract

In most (weakly interacting) extensions of the Standard Model the relation mapping the parameter values onto experimentally measurable quantities can be computed (with some uncertainties), but the inverse relation is usually not known. In this paper we demonstrate the ability of artificial neural networks to find this unknown relation, by determining the unknown parameters of the constrained minimal supersymmetric extension of the Standard Model (CMSSM) from quantities that can be measured at the LHC. We expect that the method works also for many other new physics models. We compare its performance with the results of a straightforward χ^2 minimization. We simulate LHC signals at a center of mass energy of 14 TeV at the hadron level. In this proof-of-concept study we do not explicitly simulate Standard Model backgrounds, but apply cuts that have been shown to enhance the signal-to-background ratio. We analyze four different benchmark points that lie just beyond current lower limits on superparticle masses, each of which leads to around 1000 events after cuts for an integrated luminosity of 10 fb^{-1}. We use up to 84 observables, most of which are counting observables; we do not attempt to directly reconstruct (differences of) masses from kinematic edges or kinks of distributions. We nevertheless find that m_0 and m_{1/2} can be determined reliably, with errors as small as 1% in some cases. With 500 fb^{-1} of data tanβas well as A_0 can also be determined quite accurately. For comparable computational effort the χ^2 minimization yielded much worse results.

46 pages, 10 figures, 4 tables; added short paragraph in Section 5 about the goodness of the fit, version to appear in Phys. Rev. D

References in corpus (41)

• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
• Herwig++ Physics and Manual
• Jet substructure as a new Higgs search channel at the LHC
• Top-tagging: A Method for Identifying Boosted Hadronic Tops
• Gluino Stransverse Mass
• Measuring superparticle masses at hadron collider using the transverse mass kink
• Using Subsystem MT2 for Complete Mass Determinations in Decay Chains with Missing Energy at Hadron Colliders
• Minimal Kinematic Constraints and MT2
• The Higgs sector of the phenomenological MSSM in the light of the Higgs boson discovery
• On measuring the masses of pair-produced semi-invisibly decaying particles at hadron colliders
• Top Jets at the LHC
• Accurate Mass Determinations in Decay Chains with Missing Energy
• The generalised NMSSM at one loop: fine tuning and phenomenology
• MTGEN : Mass scale measurements in pair-production at colliders
• Transverse Observables and Mass Determination at Hadron Colliders
• Mass Determination of New States at Hadron Colliders
• The Landscape of Sparticle Mass Hierarchies and Their Signature Space at the LHC
• Inclusive transverse mass analysis for squark and gluino mass determination
• Three-Loop Corrections to the Higgs Boson Mass and Implications for Supersymmetry at the LHC
• Using kinematic boundary lines for particle mass measurements and disambiguation in SUSY-like events with missing energy
• Handling jets + missing E_T channel using inclusive mT2
• Precise reconstruction of sparticle masses without ambiguities
• Search for supersymmetry in pp collisions at sqrt(s) = 7 TeV in final states with missing transverse momentum and b-jets with the ATLAS detector
• Discovering Higgs Bosons of the MSSM using Jet Substructure
• The Precision Determination of Invisible-Particle Masses at the LHC
• A General Method for Model-Independent Measurements of Particle Spins, Couplings and Mixing Angles in Cascade Decays with Missing Energy at Hadron Colliders
• A hybrid method for determining particle masses at the Large Hadron Collider with fully identified cascade decays
• Mass determination in sequential particle decay chains
• Top Polarization and Stop Mixing from Boosted Jet Substructure
• Precision Determination of Invisible-Particle Masses at the CERN LHC: II
• Extracting the Dark Matter Mass from Single Stage Cascade Decays at the LHC
• On cascade decays of squarks at the LHC in NLO QCD
• A Simple Mass Reconstruction Technique for SUSY particles at the LHC
• Squark Cascade Decays to Charginos/Neutralinos: Gluon Radiation
• Search for supersymmetry in final states with a single lepton, b-quark jets, and missing transverse energy in proton-proton collisions at sqrt(s) = 7 TeV
• Progress in the NNPDF global analysis
• Identifying boosted hadronically decaying top quark using jet substructure in its center-of-mass frame
• Understanding and improving the Effective Mass for LHC searches
• Determining the squark mass at the LHC
• Direct and Indirect Detection of Neutralino Dark Matter and Collider Signatures in an $SO(10)$ Model with Two Intermediate Scales

Cited by in corpus (14)

• Global fits of GUT-scale SUSY models with GAMBIT
• ColliderBit: a GAMBIT module for the calculation of high-energy collider observables and likelihoods
• GUT-scale constrained SUSY in light of E989 muon g-2 measurement
• The BSM-AI project: SUSY-AI - Generalizing LHC limits on Supersymmetry with Machine Learning
• Probing stop pair production at the LHC with graph neural networks
• Unveiling CP property of top-Higgs coupling with graph neural networks at the LHC
• Status of CMSSM in light of current LHC Run-2 and LUX data
• Supervised deep learning in high energy phenomenology: a mini review
• GAMBIT and its Application in the Search for Physics Beyond the Standard Model
• Constraining resonant dark matter with combined LHC electroweakino searches
• A comparison of optimisation algorithms for high-dimensional particle and astrophysics applications
• Probing triple Higgs coupling with machine learning at the LHC
• Resolving the existence of Higgsinos in the LHC inverse problem
• SCYNet: Testing supersymmetric models at the LHC with neural networks