Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows

Abstract

We explore the use of autoregressive flows, a type of generative model with tractable likelihood, as a means of efficient generation of physical particle collider events. The usual maximum likelihood loss function is supplemented by an event weight, allowing for inference from event samples with variable, and even negative event weights. To illustrate the efficacy of the model, we perform experiments with leading-order top pair production events at an electron collider with importance sampling weights, and with next-to-leading-order top pair production events at the LHC that involve negative weights.

26 pages, 7 figures

References in corpus (66)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• An Introduction to PYTHIA 8.2
• FastJet user manual
• Matching NLO QCD computations with Parton Shower simulations: the POWHEG method
• Event generation with SHERPA 1.1
• Herwig++ Physics and Manual
• Parton distributions with LHC data
• Normalizing Flows: An Introduction and Review of Current Methods
• Cuba - a library for multidimensional numerical integration
• QCD matrix elements + parton showers: The NLO case
• Merging meets matching in MC@NLO
• Automatic spin-entangled decays of heavy resonances in Monte Carlo simulations
• CutTools: a program implementing the OPP reduction method to compute one-loop amplitudes
• General-purpose event generators for LHC physics
• Automation of one-loop QCD corrections
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• OneLOop: for the evaluation of one-loop scalar functions
• 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
• Automated one-loop calculations: a proof of concept
• Weight optimization in multichannel Monte Carlo
• Event Generation with Normalizing Flows
• Effective Sample Size for Importance Sampling based on discrepancy measures
• The Monte Carlo Event Generator AcerMC 2.0 with Interfaces to PYTHIA 6.2 and HERWIG 6.5
• Ninja: Automated Integrand Reduction via Laurent Expansion for One-Loop Amplitudes
• How to GAN LHC Events
• Parton showers beyond leading logarithmic accuracy
• Vegas Revisited: Adaptive Monte Carlo Integration Beyond Factorization
• Precision phenomenology with MCFM
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• Regressive and generative neural networks for scalar field theory
• i-flow: High-dimensional Integration and Sampling with Normalizing Flows
• Matching Parton Showers to NLO Computation
• Exploring phase space with Neural Importance Sampling
• Invertible Networks or Partons to Detector and Back Again
• Fast and accurate simulation of particle detectors using generative adversarial networks
• Triple collinear emissions in parton showers
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• Implementing NLO DGLAP evolution in Parton Showers
• How to GAN away Detector Effects
• Integrand reduction of one-loop scattering amplitudes through Laurent series expansion
• Leading-color fully differential two-loop soft corrections to QCD dipole showers
• Neural Network-Based Approach to Phase Space Integration
• Simulation of vector boson plus many jet final states at the high luminosity LHC
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
• Parton showers with more exact color evolution
• Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks
• Color matrix element corrections for parton showers
• Deep Learning as a Parton Shower
• Lund jet images from generative and cycle-consistent adversarial networks
• Foam: Multi-Dimensional General Purpose Monte Carlo Generator With Self-Adapting Simplical Grid
• On the reduction of negative weights in MC@NLO-type matching procedures
• Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks
• Using neural networks for efficient evaluation of high multiplicity scattering amplitudes
• Improved Neural Network Monte Carlo Simulation
• GANs for generating EFT models
• VegasFlow: accelerating Monte Carlo simulation across multiple hardware platforms
• Cherenkov Detectors Fast Simulation Using Neural Networks
• Exhaustive Neural Importance Sampling applied to Monte Carlo event generation
• Particle Generative Adversarial Networks for full-event simulation at the LHC and their application to pileup description
• A Positive Resampler for Monte Carlo Events with Negative Weights
• Machine Learning Templates for QCD Factorization in the Search for Physics Beyond the Standard Model
• How to GAN Event Subtraction
• Fast computation of MadGraph amplitudes on graphics processing unit (GPU)
• Computational challenges for MC event generation

Cited by in corpus (37)

• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Machine Learning and LHC Event Generation
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Understanding Event-Generation Networks via Uncertainties
• Event Generators for High-Energy Physics Experiments
• Accelerating Monte Carlo event generation -- rejection sampling using neural network event-weight estimates
• Generative Networks for Precision Enthusiasts
• A factorisation-aware Matrix element emulator
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• Optimising simulations for diphoton production at hadron colliders using amplitude neural networks
• Targeting Multi-Loop Integrals with Neural Networks
• MadNIS -- Neural Multi-Channel Importance Sampling
• Presenting Unbinned Differential Cross Section Results
• How to Understand Limitations of Generative Networks
• Two Invertible Networks for the Matrix Element Method
• Measuring QCD Splittings with Invertible Networks
• Vector Boson Scattering Processes: Status and Prospects
• ν-Flows: Conditional Neutrino Regression
• The MadNIS Reloaded
• One-loop matrix element emulation with factorisation awareness
• CaloFlow for CaloChallenge Dataset 1
• Unweighting multijet event generation using factorisation-aware neural networks
• Precision-Machine Learning for the Matrix Element Method
• ELSA -- Enhanced latent spaces for improved collider simulations
• Multi-variable Integration with a Neural Network
• Differentiable MadNIS-Lite
• Exploring phase space with Nested Sampling
• Anomaly detection with flow-based fast calorimeter simulators
• How to GAN Event Unweighting
• Accelerating multijet-merged event generation with neural network matrix element surrogates
• TopicFlow: Disentangling quark and gluon jets with normalizing flows
• Unifying Simulation and Inference with Normalizing Flows
• Variance Reduction via Simultaneous Importance Sampling and Control Variates Techniques Using Vegas
• Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics
• Event Generation and Density Estimation with Surjective Normalizing Flows
• Generators and the (Accelerated) Future
• Data-Driven Predictions for Dark Photon and Millicharged Particle Production