How to GAN away Detector Effects

Abstract

LHC analyses directly comparing data and simulated events bear the danger of using first-principle predictions only as a black-box part of event simulation. We show how simulations, for instance, of detector effects can instead be inverted using generative networks. This allows us to reconstruct parton level information from measured events. Our results illustrate how, in general, fully conditional generative networks can statistically invert Monte Carlo simulations. As a technical by-product we show how a maximum mean discrepancy loss can be staggered or cooled.

arXiv comment16 pages, 13 figures

References in corpus (29)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• The anti-k_t jet clustering algorithm
• A Brief Introduction to PYTHIA 8.1
• FastJet user manual
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Measurement of the differential cross section for top quark pair production in pp collisions at sqrt(s) = 8 TeV
• A Monte Carlo global analysis of the Standard Model Effective Field Theory: the top quark sector
• O new physics, where art thou? A global search in the top sector
• How to GAN LHC Events
• Constraining anomalous Higgs boson couplings to the heavy flavor fermions using matrix element techniques
• Measurements of top-quark pair differential cross-sections in the lepton+jets channel in $pp$ collisions at $\sqrt{s}=8$ TeV using the ATLAS detector
• A Guide to Constraining Effective Field Theories with Machine Learning
• Constraining top quark effective theory in the LHC Run II era
• The Gauge-Higgs Legacy of the LHC Run II
• Vices and Virtues of Higgs EFTs at Large Energy
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Pushing Higgs Effective Theory to its Limits
• Fast and accurate simulation of particle detectors using generative adversarial networks
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• Deep Learning as a Parton Shower
• Extending the Matrix Element Method beyond the Born approximation: Calculating event weights at next-to-leading order accuracy
• Reweighting a parton shower using a neural network: the final-state case
• Benchmarking simplified template cross sections in $WH$ production
• The Matrix Element Method at next-to-leading order QCD for hadronic collisions: Single top-quark production at the LHC as an example application
• Matrix Element Method at NLO for (anti-)${\mathbf{k}}_{\mathbf{t}}$-jet algorithms

Cited by in corpus (64)

• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Machine Learning and LHC Event Generation
• Invertible Networks or Partons to Detector and Back Again
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Understanding Event-Generation Networks via Uncertainties
• Event Generators for High-Energy Physics Experiments
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• Generative Networks for Precision Enthusiasts
• GANplifying Event Samples
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• A factorisation-aware Matrix element emulator
• Targeting Multi-Loop Integrals with Neural Networks
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
• Phenomenology of jet angularities at the LHC
• Presenting Unbinned Differential Cross Section Results
• Style-based quantum generative adversarial networks for Monte Carlo events
• Improved Neural Network Monte Carlo Simulation
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• How to Understand Limitations of Generative Networks
• Two Invertible Networks for the Matrix Element Method
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Towards a Deep Learning Model for Hadronization
• The MadNIS Reloaded
• Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Improving Generative Model-based Unfolding with Schrödinger Bridges
• Returning CP-Observables to The Frames They Belong
• How to GAN Event Subtraction
• CaloDREAM -- Detector Response Emulation via Attentive flow Matching
• The Landscape of Unfolding with Machine Learning
• Precision-Machine Learning for the Matrix Element Method
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• A simultaneous unbinned differential cross section measurement of twenty-four $Z$+jets kinematic observables with the ATLAS detector
• A Lorentz-Equivariant Transformer for All of the LHC
• Compressing PDF sets using generative adversarial networks
• Normalizing Flows for High-Dimensional Detector Simulations
• Parameter Estimation using Neural Networks in the Presence of Detector Effects
• A Novel Scenario in the Semi-constrained NMSSM
• Optimizing Observables with Machine Learning for Better Unfolding
• Unbinned Profiled Unfolding
• Differentiable MadNIS-Lite
• Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
• Uncertainties associated with GAN-generated datasets in high energy physics
• CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation
• Accurate Surrogate Amplitudes with Calibrated Uncertainties
• How to GAN Event Unweighting
• Moment Unfolding
• Generative Invertible Quantum Neural Networks
• Generative Unfolding with Distribution Mapping
• Unifying Simulation and Inference with Normalizing Flows
• Top-philic Machine Learning
• Machine Learning-Assisted Unfolding for Neutrino Cross-section Measurements with the OmniFold Technique
• Synthesis of pulses from particle detectors with a Generative Adversarial Network (GAN)
• Extrapolating Jet Radiation with Autoregressive Transformers
• A Practical Guide to Unbinned Unfolding
• Designing Observables for Measurements with Deep Learning
• Preserving New Physics while Simultaneously Unfolding All Observables
• Tools for Unbinned Unfolding
• Reconstructing Sparticle masses at the LHC using Generative Machine Learning
• How to Unfold Top Decays
• Response Matrix Estimation in Unfolding Differential Cross Sections
• Implicit Quantile Networks For Emulation in Jet Physics