Pileup Mitigation with Machine Learning (PUMML)

Abstract

Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network takes as input the energy distribution of charged leading vertex particles, charged pileup particles, and all neutral particles and outputs the energy distribution of particles coming from leading vertex alone. The PUMML algorithm performs remarkably well at eliminating pileup distortion on a wide range of simple and complex jet observables. We test the robustness of the algorithm in a number of ways and discuss how the network can be trained directly on data.

20 pages, 8 figures, 2 tables. Updated to JHEP version

References in corpus (35)

• Adam: A Method for Stochastic Optimization
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• Jet substructure as a new Higgs search channel at the LHC
• Particle-flow reconstruction and global event description with the CMS detector
• Pileup subtraction using jet areas
• Soft Drop
• Description and performance of track and primary-vertex reconstruction with the CMS tracker
• Determination of Jet Energy Calibration and Transverse Momentum Resolution in CMS
• Jet Trimming
• Jet energy scale and resolution in the CMS experiment in pp collisions at 8 TeV
• Topological cell clustering in the ATLAS calorimeters and its performance in LHC Run 1
• Performance of pile-up mitigation techniques for jets in $pp$ collisions at $\sqrt{s}=8$ TeV using the ATLAS detector
• Jet energy measurement with the ATLAS detector in proton-proton collisions at sqrt(s) = 7 TeV
• Energy Correlation Functions for Jet Substructure
• Jet substructure as a new Higgs search channel at the LHC
• Jet energy scale measurements and their systematic uncertainties in proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Pileup Per Particle Identification
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Recombination Algorithms and Jet Substructure: Pruning as a Tool for Heavy Particle Searches
• Techniques for improved heavy particle searches with jet substructure
• 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
• Deep-learning Top Taggers or The End of QCD?
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Jet Observables Without Jet Algorithms
• SoftKiller, a particle-level pileup removal method
• Weakly Supervised Classification in High Energy Physics
• Particle-level pileup subtraction for jets and jet shapes
• Jet Cleansing: Pileup Removal at High Luminosity
• Identification and rejection of pile-up jets at high pseudorapidity with the ATLAS detector

Cited by in corpus (75)

• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Jet Substructure at the Large Hadron Collider: Experimental Review
• Classification without labels: Learning from mixed samples in high energy physics
• Searching for New Physics with Deep Autoencoders
• Machine Learning in Nuclear Physics
• Energy Flow Networks: Deep Sets for Particle Jets
• Deep-learned Top Tagging with a Lorentz Layer
• QCD or What?
• Energy flow polynomials: A complete linear basis for jet substructure
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• The Lund Jet Plane
• The Metric Space of Collider Events
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Learning to Classify from Impure Samples with High-Dimensional Data
• ABCNet: An attention-based method for particle tagging
• Boosting $H\to b\bar{b}$ with Machine Learning
• Modern Machine Learning and Particle Physics
• Jet Charge and Machine Learning
• A robust anomaly finder based on autoencoders
• Recursive Soft Drop
• Quark-Gluon Tagging: Machine Learning vs Detector
• An operational definition of quark and gluon jets
• Deep-Learning Jets with Uncertainties and More
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Supervised deep learning in high energy phenomenology: a mini review
• Lund jet images from generative and cycle-consistent adversarial networks
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• The Hidden Geometry of Particle Collisions
• Reweighting a parton shower using a neural network: the final-state case
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data
• Unleashing the full power of LHCb to probe Stealth New Physics
• Pileup and Underlying Event Mitigation with Iterative Constituent Subtraction
• Looking for Minimal Inverse Seesaw scenarios at the LHC with Jet Substructure Techniques
• Electroweak ALP Searches at a Muon Collider
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• Electromagnetic Showers Beyond Shower Shapes
• Probing the Triple Higgs Self-Interaction at the Large Hadron Collider
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Opening the black box of neural nets: case studies in stop/top discrimination
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Explainable machine learning of the underlying physics of high-energy particle collisions
• Higgs self-coupling measurements using deep learning in the $b\bar{b}b\bar{b}$ final state
• Which Metric on the Space of Collider Events?
• Pile-Up Mitigation using Attention
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• CapsNets Continuing the Convolutional Quest
• The importance of calorimetry for highly-boosted jet substructure
• Jet grooming through reinforcement learning
• Invisible Higgs search through Vector Boson Fusion: A deep learning approach
• Optimizing Observables with Machine Learning for Better Unfolding
• Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics
• Learning to Inflate
• Quark jet rates and quark/gluon discrimination in multi-jet final states
• Fast convolutional neural networks for identifying long-lived particles in a high-granularity calorimeter
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Semi-supervised Graph Neural Networks for Pileup Noise Removal
• Heterogeneous Graph Neural Network for Identifying Hadronically Decayed Tau Leptons at the High Luminosity LHC
• Jet Timing
• Pileup mitigation at the Large Hadron Collider with Graph Neural Networks
• Learning Physics at Future $e^{-}{e}^{+}$ Colliders with Machine
• Pileup and Infrared Radiation Annihilation (PIRANHA): A Paradigm for Continuous Jet Grooming
• Deep Learning Jet Substructure from Two-Particle Correlation
• Optimal transport for a novel event description at hadron colliders
• Jet Single Shot Detection
• Subtracted Cumulants: Mitigating Large Background in Jet Substructure
• Safety of Quark/Gluon Jet Classification
• PAIReD jet: A multi-pronged resonance tagging strategy across all Lorentz boosts
• A background estimator for jet studies in p+p and A+A collisions
• Deep-learning-based decomposition of overlapping-sparse images: application at the vertex of neutrino interactions
• Deep Image Reconstruction for Background Subtraction in Heavy-Ion Collisions
• Image-Based Jet Analysis
• Shape-based event pileup separation in Troitsk nu-mass experiment
• Variational inference for pile-up removal at hadron colliders with diffusion models
• Energy Flow in Particle Collisions