Neural Networks for Full Phase-space Reweighting and Parameter Tuning

Abstract

Precise scientific analysis in collider-based particle physics is possible because of complex simulations that connect fundamental theories to observable quantities. The significant computational cost of these programs limits the scope, precision, and accuracy of Standard Model measurements and searches for new phenomena. We therefore introduce Deep neural networks using Classification for Tuning and Reweighting (DCTR), a neural network-based approach to reweight and fit simulations using all kinematic and flavor information -- the full phase space. DCTR can perform tasks that are currently not possible with existing methods, such as estimating non-perturbative fragmentation uncertainties. The core idea behind the new approach is to exploit powerful high-dimensional classifiers to reweight phase space as well as to identify the best parameters for describing data. Numerical examples from $e^{+}{e}^{-}\to \text{jets}$ demonstrate the fidelity of these methods for simulation parameters that have a big and broad impact on phase space as well as those that have a minimal and/or localized impact. The high fidelity of the full phase-space reweighting enables a new paradigm for simulations, parameter tuning, and model systematic uncertainties across particle physics and possibly beyond.

arXiv comment7 pages, 3 figures; v2 has updated citations and clarifications; v3 has a new appendix with an alternative fitting method

References in corpus (55)

• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The anti-k_t jet clustering algorithm
• The cosmological simulation code GADGET-2
• An Introduction to PYTHIA 8.2
• FastJet user manual
• LHAPDF6: parton density access in the LHC precision era
• PDF4LHC recommendations for LHC Run II
• Dispelling the N^3 myth for the Kt jet-finder
• Tuning PYTHIA 8.1: the Monash 2013 Tune
• Identifying Boosted Objects with N-subjettiness
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• ParticleNet: Jet Tagging via Particle Clouds
• Energy Correlation Functions for Jet Substructure
• Maximizing Boosted Top Identification by Minimizing N-subjettiness
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• The population of galaxy-galaxy strong lenses in forthcoming optical imaging surveys
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Systematic event generator tuning for the LHC
• Anomaly Detection for Resonant New Physics with Machine Learning
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Energy Flow Networks: Deep Sets for Particle Jets
• Parameterized Machine Learning for High-Energy Physics
• Learning New Physics from a Machine
• Extending the Bump Hunt with Machine Learning
• Deep-learned Top Tagging with a Lorentz Layer
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Mining gold from implicit models to improve likelihood-free inference
• Constraining Effective Field Theories with Machine Learning
• A Guide to Constraining Effective Field Theories with Machine Learning
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Automated Parton-Shower Variations in Pythia 8
• Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
• QCD-Aware Recursive Neural Networks for Jet Physics
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Reweighting QCD matrix-element and parton-shower calculations
• 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
• Reweighting with Boosted Decision Trees
• Deep Sets
• Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
• Reweighting Parton Showers
• Measurements of two-particle correlations in $e^{+}{e}^{-}$ collisions at 91 GeV with ALEPH archived data
• Deep Learning as a Parton Shower
• Generative Models for Fast Calorimeter Simulation.LHCb case
• Reweighting a parton shower using a neural network: the final-state case
• Observation of the decays ${\Lambda }_b^0\to {\chi }_{c1}p{K}^{-}$ and ${\Lambda }_b^0\to {\chi }_{c2}p{K}^{-}$
• Search for pair production of higgsinos in final states with at least three $b$-tagged jets in $\sqrt{s}=13$ TeV $pp$ collisions using the ATLAS detector
• Event generator tuning using Bayesian optimization
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• Adapting the serial Alpgen event generator to simulate LHC collisions on millions of parallel threads

Cited by in corpus (48)

• The frontier of simulation-based inference
• OmniFold: A Method to Simultaneously Unfold All Observables
• Simulation Assisted Likelihood-free Anomaly Detection
• Challenges in Monte Carlo event generator software for High-Luminosity LHC
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• Event Generators for High-Energy Physics Experiments
• GANplifying Event Samples
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Measurements of polarization and spin correlation and observation of entanglement in top quark pairs using lepton+jets events from proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Towards a Deep Learning Model for Hadronization
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Learning Likelihood Ratios with Neural Network Classifiers
• ELSA -- Enhanced latent spaces for improved collider simulations
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Observation of gauge boson joint-polarisation states in $W^{\pm }Z$ production from $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Parameter Estimation using Neural Networks in the Presence of Detector Effects
• Unbinned Profiled Unfolding
• Reframing Jet Physics with New Computational Methods
• Non-Parametric Data-Driven Background Modelling using Conditional Probabilities
• Towards a data-driven model of hadronization using normalizing flows
• MCNNTUNES: tuning Shower Monte Carlo generators with machine learning
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Parameter Inference from Event Ensembles and the Top-Quark Mass
• Evidence for longitudinally polarized $W$ bosons in the electroweak production of same-sign $W$ boson pairs in association with two jets in pp collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Neural Conditional Reweighting
• Jet Classification Using High-Level Features from Anatomy of Top Jets
• A Bayesian tune of the Herwig Monte Carlo event generator
• Reweighting simulated events using machine-learning techniques in the CMS experiment
• Efficiency Parameterization with Neural Networks
• Describing Hadronization via Histories and Observables for Monte-Carlo Event Reweighting
• Refining fast simulation using machine learning
• Latent Space Refinement for Deep Generative Models
• Designing Observables for Measurements with Deep Learning
• BitHEP -- The Limits of Low-Precision ML in HEP
• Fast Perfekt: Regression-based refinement of fast simulation
• One flow to correct them all: improving simulations in high-energy physics with a single normalising flow and a switch
• Applying Machine Learning Techniques To Intermediate-Length Cascade Decays
• Observable Optimization for Precision Theory: Machine Learning Energy Correlators
• Quantifying EFT Uncertainties in LHC Searches
• Differential cross section measurements of top quark pair production for variables of the dineutrino system with the CMS experiment
• Machine learning in top quark physics at ATLAS and CMS
• Strong CWoLa: Binary Classification Without Background Simulation
• Reweighting and Analysing Event Generator Systematics by Neural Networks on High-Level Features
• Improving statistical precision in Monte Carlo samples with negative weights via reweighting and uncertainty quantification