Exploring phase space with Neural Importance Sampling

Abstract

We present a novel approach for the integration of scattering cross sections and the generation of partonic event samples in high-energy physics. We propose an importance sampling technique capable of overcoming typical deficiencies of existing approaches by incorporating neural networks. The method guarantees full phase space coverage and the exact reproduction of the desired target distribution, in our case given by the squared transition matrix element. We study the performance of the algorithm for a few representative examples, including top-quark pair production and gluon scattering into three- and four-gluon final states.

19 pages, 6 figures, updated references, extended discussion

References in corpus (31)

• 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
• An Introduction to PYTHIA 8.2
• A general framework for implementing NLO calculations in shower Monte Carlo programs: the POWHEG BOX
• Event generation with SHERPA 1.1
• Herwig++ Physics and Manual
• MadGraph/MadEvent v4: The New Web Generation
• Scattering Amplitudes with Open Loops
• Comix, a new matrix element generator
• Event Generation with Sherpa 2.2
• Cuba - a library for multidimensional numerical integration
• WHIZARD: Simulating Multi-Particle Processes at LHC and ILC
• General-purpose event generators for LHC physics
• AMEGIC++ 1.0, A Matrix Element Generator In C++
• RECOLA: REcursive Computation of One-Loop Amplitudes
• Weight optimization in multichannel Monte Carlo
• Event Generation with Normalizing Flows
• Recursive generation of one-loop amplitudes in the Standard Model
• How to GAN LHC Events
• Vegas Revisited: Adaptive Monte Carlo Integration Beyond Factorization
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• Beyond Standard Model calculations with Sherpa
• Simulation of vector boson plus many jet final states at the high luminosity LHC
• Foam: A General-Purpose Cellular Monte Carlo Event Generator
• A hierarchical phase space generator for QCD antenna structures
• Foam: Multi-Dimensional General Purpose Monte Carlo Generator With Self-Adapting Simplical Grid
• Learning to Importance Sample in Primary Sample Space
• (MC)**3 -- a Multi-Channel Markov Chain Monte Carlo algorithm for phase-space sampling
• The Metropolis algorithm for on-shell four-momentum phase space
• A Forward Branching Phase Space Generator for Hadron colliders
• Generating QCD-antennas

Cited by in corpus (74)

• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Machine Learning and LHC Event Generation
• i-flow: High-dimensional Integration and Sampling with Normalizing Flows
• 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
• Challenges in Monte Carlo event generator software for High-Luminosity LHC
• Event Generators for High-Energy Physics Experiments
• Accelerating Monte Carlo event generation -- rejection sampling using neural network event-weight estimates
• Neural Network-Based Approach to Phase Space Integration
• Generative Networks for Precision Enthusiasts
• GANplifying Event Samples
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• A factorisation-aware Matrix element emulator
• Optimising simulations for diphoton production at hadron colliders using amplitude neural networks
• Targeting Multi-Loop Integrals with Neural Networks
• Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• MadNIS -- Neural Multi-Channel Importance Sampling
• Using neural networks for efficient evaluation of high multiplicity scattering amplitudes
• Improved Neural Network Monte Carlo Simulation
• How to Understand Limitations of Generative Networks
• Two Invertible Networks for the Matrix Element Method
• Local Unitarity: a representation of differential cross-sections that is locally free of infrared singularities at any order
• Measuring QCD Splittings with Invertible Networks
• Vector Boson Scattering Processes: Status and Prospects
• 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
• Efficient phase-space generation for hadron collider event simulation
• CaloFlow for CaloChallenge Dataset 1
• Exhaustive Neural Importance Sampling applied to Monte Carlo event generation
• Unweighting multijet event generation using factorisation-aware neural networks
• One-loop matrix element emulation with factorisation awareness
• CaloDREAM -- Detector Response Emulation via Attentive flow Matching
• Precision-Machine Learning for the Matrix Element Method
• Multi-variable Integration with a Neural Network
• Matrix Element Regression with Deep Neural Networks -- breaking the CPU barrier
• Unbiased Elimination of Negative Weights in Monte Carlo Samples
• Normalizing Flows for High-Dimensional Detector Simulations
• A novel event generator for the automated simulation of neutrino scattering
• A Portable Parton-Level Event Generator for the High-Luminosity LHC
• Calorimeter shower superresolution
• Differentiable MadNIS-Lite
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• Differentiable Matrix Elements with MadJax
• Exploring phase space with Nested Sampling
• Multi-variable integration with a variational quantum circuit
• Uncertainties associated with GAN-generated datasets in high energy physics
• Accurate Surrogate Amplitudes with Calibrated Uncertainties
• Anomaly detection with flow-based fast calorimeter simulators
• Sampling NNLO QCD phase space with normalizing flows
• Normalizing flows for microscopic many-body calculations: an application to the nuclear equation of state
• OASIS: Optimal Analysis-Specific Importance Sampling for event generation
• Efficient negative-weight elimination in large high-multiplicity Monte Carlo event samples
• Machine Learning Post-Minkowskian Integrals
• Accelerating multijet-merged event generation with neural network matrix element surrogates
• TopicFlow: Disentangling quark and gluon jets with normalizing flows
• How to GAN Event Unweighting
• Unifying Simulation and Inference with Normalizing Flows
• Extrapolating Jet Radiation with Autoregressive Transformers
• BitHEP -- The Limits of Low-Precision ML in HEP
• Amplitude Uncertainties Everywhere All at Once
• Variance Reduction via Simultaneous Importance Sampling and Control Variates Techniques Using Vegas
• Towards a Fully Automated Differential ${\text{NNLO}}_{\text{EW}}$ Generator for Lepton Colliders
• Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics
• Focused Angular $N$-Body Event Generator (FANG)
• Event Generation and Density Estimation with Surjective Normalizing Flows
• Amplitude Surrogates for Multi-Jet Processes
• Monte Carlo Event Generators
• Generators and the (Accelerated) Future
• On the simulated kinematic distributions of heavy meson decays
• Data-Driven Predictions for Dark Photon and Millicharged Particle Production
• Monte Carlo Event Generators for Future Lepton Colliders