Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders

Abstract

We study how to use Deep Variational Autoencoders for a fast simulation of jets of particles at the LHC. We represent jets as a list of constituents, characterized by their momenta. Starting from a simulation of the jet before detector effects, we train a Deep Variational Autoencoder to return the corresponding list of constituents after detection. Doing so, we bypass both the time-consuming detector simulation and the collision reconstruction steps of a traditional processing chain, speeding up significantly the events generation workflow. Through model optimization and hyperparameter tuning, we achieve state-of-the-art precision on the jet four-momentum, while providing an accurate description of the constituents momenta, and an inference time comparable to that of a rule-based fast simulation.

arXiv comment11 pages, 8 figures

References in corpus (34)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• Generative Adversarial Networks
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Variational Inference with Normalizing Flows
• Particle-flow reconstruction and global event description with the CMS detector
• Jet reconstruction and performance using particle flow with the ATLAS Detector
• 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
• A Roadmap for HEP Software and Computing R&D for the 2020s
• Search for new phenomena in dijet events using 37 fb${}^{-1}$ of $pp$ collision data collected at $\sqrt{s}=$13 TeV with the ATLAS detector
• Graph Neural Networks in Particle Physics
• Search for narrow resonances decaying to dijets in proton-proton collisions at sqrt(s) = 13 TeV
• How to GAN LHC Events
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Search for high mass dijet resonances with a new background prediction method in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• AtlFast3: the next generation of fast simulation in ATLAS
• Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
• 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
• Measurement of jet substructure observables in $\mathrm{t}\overline{\mathrm{t}}$ events from proton-proton collisions at $\sqrt{s}=$ 13TeV
• Search for new physics in dijet angular distributions using proton-proton collisions at $\sqrt{s}=$ 13 TeV and constraints on dark matter and other models
• Lund jet images from generative and cycle-consistent adversarial networks
• Measurement of jet-substructure observables in top quark, $W$ boson and light jet production in proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Study of quark and gluon jet substructure in Z+jet and dijet events from pp collisions
• Particle Generative Adversarial Networks for full-event simulation at the LHC and their application to pileup description
• Fast computation of MadGraph amplitudes on graphics processing unit (GPU)
• Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• HEP Software Foundation Community White Paper Working Group --- Visualization

Cited by in corpus (12)

• Score-based Generative Models for Calorimeter Shower Simulation
• Evaluating generative models in high energy physics
• EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets
• Towards a Deep Learning Model for Hadronization
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Lorentz group equivariant autoencoders
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Prediction of the morphological evolution of a splashing drop using an encoder-decoder
• Set-Conditional Set Generation for Particle Physics
• LHC Hadronic Jet Generation Using Convolutional Variational Autoencoders with Normalizing Flows
• Semi-supervised permutation invariant particle-level anomaly detection
• Reconstructing Sparticle masses at the LHC using Generative Machine Learning