Variational inference for pile-up removal at hadron colliders with diffusion models

Abstract

In this paper, we present a novel method for pile-up removal of $pp$ interactions using variational inference with diffusion models, called vipr. Instead of using classification methods to identify which particles are from the primary collision, a generative model is trained to predict the constituents of the hard-scatter particle jets with pile-up removed. This results in an estimate of the full posterior over hard-scatter jet constituents, which has not yet been explored in the context of pile-up removal, yielding a clear advantage over existing methods especially in the presence of imperfect detector efficiency. We evaluate the performance of vipr in a sample of jets from simulated $t\bar{t}$ events overlain with pile-up contamination. vipr outperforms softdrop and has comparable performance to puppiml in predicting the substructure of the hard-scatter jets over a wide range of pile-up scenarios.

19 pages, 13 figures

References in corpus (52)

• 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
• FastJet user manual
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Parton distributions with LHC data
• LHAPDF6: parton density access in the LHC precision era
• Jet substructure as a new Higgs search channel at the LHC
• Identifying Boosted Objects with N-subjettiness
• The CMS trigger system
• Soft Drop
• Automatic spin-entangled decays of heavy resonances in Monte Carlo simulations
• Performance of pile-up mitigation techniques for jets in $pp$ collisions at $\sqrt{s}=8$ TeV using the ATLAS detector
• Top-tagging: A Method for Identifying Boosted Hadronic Tops
• Towards Jetography
• Energy Correlation Functions for Jet Substructure
• Pileup Per Particle Identification
• Measurement of the Inelastic Proton-Proton Cross Section at $\sqrt{s}=13$ TeV with the ATLAS Detector at the LHC
• Power Counting to Better Jet Observables
• Measurement of the inelastic proton-proton cross section at $\sqrt{s}=$ 13 TeV
• Luminosity determination in $pp$ collisions at $\sqrt{s}=13$ TeV using the ATLAS detector at the LHC
• Pileup mitigation at CMS in 13 TeV data
• Pileup subtraction for jet shapes
• Reconstruction of primary vertices at the ATLAS experiment in Run 1 proton-proton collisions at the LHC
• Pileup Mitigation with Machine Learning (PUMML)
• SoftKiller, a particle-level pileup removal method
• Score-based Generative Models for Calorimeter Shower Simulation
• Search for heavy particles decaying into top-quark pairs using lepton-plus-jets events in proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Particle-level pileup subtraction for jets and jet shapes
• A measurement of the soft-drop jet mass in pp collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• A measurement of soft-drop jet observables in $pp$ collisions with the ATLAS detector at $\sqrt{s}=13$ TeV
• A search for ttbar resonances in lepton+jets events with highly boosted top quarks collected in pp collisions at sqrt(s) = 7 TeV with the ATLAS detector
• Fast Point Cloud Generation with Diffusion Models in High Energy Physics
• Jet Cleansing: Pileup Removal at High Luminosity
• Identification and rejection of pile-up jets at high pseudorapidity with the ATLAS detector
• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• Search for resonant $\mathrm{t}\overline{\mathrm{t}}$ production in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Optimisation of large-radius jet reconstruction for the ATLAS detector in 13 TeV proton-proton collisions
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• ν-Flows: Conditional Neutrino Regression
• The MadNIS Reloaded
• The ATLAS Trigger System for LHC Run 3 and Trigger performance in 2022
• PC-Droid: Faster diffusion and improved quality for particle cloud generation
• Software Performance of the ATLAS Track Reconstruction for LHC Run 3
• High-dimensional and Permutation Invariant Anomaly Detection
• ${\nu }^2$-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows
• Pile-Up Mitigation using Attention
• Jet grooming through reinforcement learning
• Semi-supervised Graph Neural Networks for Pileup Noise Removal
• Luminosity determination using Z boson production at the CMS experiment
• Measurement of boosted Higgs bosons produced via vector boson fusion or gluon fusion in the H $\to$ $\mathrm{b}\bar{\mathrm{b}}$ decay mode using LHC proton-proton collision data at $\sqrt{s}$ = 13 TeV
• RODEM Jet Datasets