Reconstructing Sparticle masses at the LHC using Generative Machine Learning

Abstract

We explore a generative model framework to infer the masses of heavy particles from detector-level data over a broad parameter space. Our model combines a transformer-based detector encoder and a diffusion neural network. We first apply our model to a new physics scenario involving the pair production of wino-like chargino-neutralino, $pp\to {\tilde{\chi }}_1^{\pm }{\tilde{\chi }}_2^0$, in the $1\ell +2\gamma +jets$ channel at the high luminosity LHC~(HL-LHC). We find that our framework can achieve mass reconstruction efficiency of $\gtrsim 70\%$ for the lightest neutralino ${\tilde{\chi }}_1^0$ and $\gtrsim 40\%$ for the second lightest neutralino ${\tilde{\chi }}_2^0$, for a mass tolerance of $\Delta m=30$GeV, across the entire parameter space accessible at the HL-LHC. We further extend our analysis to a different scenario with $pp\to {\tilde{\chi }}_1^{\pm }{\tilde{\chi }}_1^{\mp }+{\tilde{\chi }}_1^{\pm }{\tilde{\chi }}_2^0$ pair production at the HL-LHC in the $4\ell +\mathrm{E}{/}_{\mathrm{T}}$ channel, and for a fixed value of $m_{{\tilde{\chi }}_2^0}$, we obtain reconstruction efficiencies $\gtrsim 80\%$ over a wide range of $m_{{\tilde{\chi }}_1^0}$ for $\Delta m=30$GeV.

17 pages, 7 figures and 1 table, New results and discussions added

References in corpus (33)

• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• R-parity violating supersymmetry
• Rotation Curves of Spiral Galaxies
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• First measurement of neutrino oscillation parameters using neutrinos and antineutrinos by NOvA
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Final results of Borexino Phase-I on low energy solar neutrino spectroscopy
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Measurement of electron antineutrino oscillation with 1958 days of operation at Daya Bay
• Event Generation with Normalizing Flows
• Measurement of Reactor Antineutrino Oscillation Amplitude and Frequency at RENO
• Search for CP violation in Neutrino and Antineutrino Oscillations by the T2K experiment with $2.2\times 10^{21}$ protons on target
• How to GAN LHC Events
• Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
• Invertible Networks or Partons to Detector and Back Again
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• How to GAN away Detector Effects
• Atmospheric Neutrino Oscillation Analysis With Improved Event Reconstruction in Super-Kamiokande IV
• Fast Point Cloud Generation with Diffusion Models in High Energy Physics
• Search for supersymmetry in events with four or more charged leptons in $139\,\mbox{fb\(^{-1}\)}$ of $\sqrt{s}=13$ TeV $pp$ collisions with the ATLAS detector
• Two Invertible Networks for the Matrix Element Method
• Deep generative models for fast photon shower simulation in ATLAS
• The ABC of RPV: Classification of R-Parity Violating Signatures at the LHC for Small Couplings
• The Landscape of Unfolding with Machine Learning
• Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
• Electroweakino searches at the HL-LHC in the baryon number violating MSSM
• Bilinear R-parity violating supersymmetry under the light of neutrino oscillation, higgs and flavor data
• Improving sensitivity of trilinear RPV SUSY searches using machine learning at the LHC
• The ABC of RPV II: Classification of R-parity Violating Signatures from UDD Couplings and their Coverage at the LHC
• Generative Unfolding with Distribution Mapping
• Probing sub-TeV Higgsinos aided by a ML-based top tagger in the context of Trilinear RPV SUSY