Jet Flavor Classification in High-Energy Physics with Deep Neural Networks

Abstract

Classification of jets as originating from light-flavor or heavy-flavor quarks is an important task for inferring the nature of particles produced in high-energy collisions. The large and variable dimensionality of the data provided by the tracking detectors makes this task difficult. The current state-of-the-art tools require expert data-reduction to convert the data into a fixed low-dimensional form that can be effectively managed by shallow classifiers. We study the application of deep networks to this task, attempting classification at several levels of data, starting from a raw list of tracks. We find that the highest-level lowest-dimensionality expert information sacrifices information needed for classification, that the performance of current state-of-the-art taggers can be matched or slightly exceeded by deep-network-based taggers using only track and vertex information, that classification using only lowest-level highest-dimensionality tracking information remains a difficult task for deep networks, and that adding lower-level track and vertex information to the classifiers provides a significant boost in performance compared to the state-of-the-art.

arXiv comment12 pages, submitted to PRD

References in corpus (15)

• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• LSTM: A Search Space Odyssey
• Improving neural networks by preventing co-adaptation of feature detectors
• The anti-k_t jet clustering algorithm
• FastJet user manual
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Identification of b-quark jets with the CMS experiment
• Performance of $b$-Jet Identification in the ATLAS Experiment
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Delphes, a framework for fast simulation of a generic collider experiment
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• A search for top squarks with R-parity-violating decays to all-hadronic final states with the ATLAS detector in $\sqrt{s}$ = 8 TeV proton-proton collisions
• Search for single production of a vector-like quark via a heavy gluon in the $4b$ final state with the ATLAS detector in $pp$ collisions at $\sqrt{s}=8$ TeV

Cited by in corpus (100)

• Machine learning and the physical sciences
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• Fast inference of deep neural networks in FPGAs for particle physics
• ParticleNet: Jet Tagging via Particle Clouds
• Deep Learning and its Application to LHC Physics
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Learning New Physics from a Machine
• New Angles on Energy Correlation Functions
• Search for resonant pair production of Higgs bosons decaying to two bottom quark-antiquark pairs in proton-proton collisions at 8 TeV
• What is the Machine Learning?
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Combined search for electroweak production of charginos and neutralinos in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Energy flow polynomials: A complete linear basis for jet substructure
• Higgs boson potential at colliders: status and perspectives
• JEDI-net: a jet identification algorithm based on interaction networks
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Optimizing Event Selection with the Random Grid Search
• Neural Networks for Full Phase-space Reweighting and Parameter Tuning
• Recursive Neural Networks in Quark/Gluon Tagging
• Finding New Physics without learning about it: Anomaly Detection as a tool for Searches at Colliders
• A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
• Novel Jet Observables from Machine Learning
• Jet Charge and Machine Learning
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• ABCDisCo: Automating the ABCD Method with Machine Learning
• An operational definition of quark and gluon jets
• Mapping Machine-Learned Physics into a Human-Readable Space
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• Vertex and Energy Reconstruction in JUNO with Machine Learning Methods
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Boosted $W/Z$ Tagging with Jet Charge and Deep Learning
• End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data
• Transverse Momentum Spectra at Threshold for Groomed Heavy Quark Jets
• Search for resonant pair production of Higgs bosons decaying to bottom quark-antiquark pairs in proton-proton collisions at 13 TeV
• Automating the Construction of Jet Observables with Machine Learning
• Deep Neural Networks for Energy and Position Reconstruction in EXO-200
• The Entropy of a Jet
• Topological Obstructions to Autoencoding
• Deep learning jet modifications in heavy-ion collisions
• Jet Flavour Tagging for Future Colliders with Fast Simulation
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Predictions for energy correlators probing substructure of groomed heavy quark jets
• Stacking machine learning classifiers to identify Higgs bosons at the LHC
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Deducing Neutron Star Equation of State Parameters Directly From Telescope Spectra with Uncertainty-Aware Machine Learning
• Topology classification with deep learning to improve real-time event selection at the LHC
• Jet-Parton Assignment in ttH Events using Deep Learning
• Hybrid Quantum-Classical Graph Convolutional Network
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• A new calibration method for charm jet identification validated with proton-proton collision events at $\sqrt{s}$ = 13 TeV
• Classification of Fermi-LAT sources with deep learning using energy and time spectra
• Search for higgsino pair production in pp collisions at sqrt(s) = 13 TeV in final states with large missing transverse momentum and two Higgs bosons decaying via H to bb-bar
• Secondary Vertex Finding in Jets with Neural Networks
• Jet grooming through reinforcement learning
• Learning to Identify Electrons
• Leveraging universality of jet taggers through transfer learning
• Classification and Recovery of Radio Signals from Cosmic Ray Induced Air Showers with Deep Learning
• Jet tagging algorithm of graph network with HaarPooling message passing
• Fractal based observables to probe jet substructure of quarks and gluons
• Machine learning techniques in searches for $t\bar{t}h$ in the $h\to b\bar{b}$ decay channel
• Tagging more quark jet flavours at FCC-ee at 91 GeV with a transformer-based neural network
• Learning Multivariate New Physics
• Jet Tagging with More-Interaction Particle Transformer
• Drell-Yan production in third-generation gauge vector leptoquark models at NLO+PS in QCD
• Modification of jet structure in high-multiplicity pp collisions due to multiple-parton interactions and observing a multiplicity-independent characteristic jet size
• Jet Discrimination with Quantum Complete Graph Neural Network
• Maximum performance of strange-jet tagging at hadron colliders
• Ultrafast jet classification on FPGAs for the HL-LHC
• Search for a third-generation leptoquark coupled to a $\tau$ lepton and a b quark through single, pair, and nonresonant production in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Sensing Higgs cascade decays through memory
• Learning Physics at Future $e^{-}{e}^{+}$ Colliders with Machine
• Machine learning classification: case of Higgs boson CP state in H to tau tau decay at LHC
• Improving Robustness of Jet Tagging Algorithms with Adversarial Training
• Deep-Learning-Based Kinematic Reconstruction for DUNE
• Jet Classification Using High-Level Features from Anatomy of Top Jets
• Improving the measurement of the Higgs boson-gluon coupling using convolutional neural networks at $e^{+}{e}^{-}$ colliders
• Role of polarizations and spin-spin correlations of $W^{\prime }s$ in $e^{-}{e}^{+}\to W^{-}{W}^{+}$ at $\sqrt{s}=250$ GeV to probe anomalous $W^{-}{W}^{+}Z/\gamma$ couplings
• Identifying Heavy-Flavor Jets Using Vectors of Locally Aggregated Descriptors
• Jet Substructure Probe on Scalar Leptoquark Models via Top Polarization
• Classify the Higgs decays with the PFN and ParticleNet at electron-positron colliders
• Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation
• Identification of additional jets in the t-tbar b-bbar events using a deep neural network
• Jet Single Shot Detection
• Top quark physics in the Large Hadron Collider era
• PAIReD jet: A multi-pronged resonance tagging strategy across all Lorentz boosts
• Jet energy calibration with deep learning as a Kubeflow pipeline
• Safety of Quark/Gluon Jet Classification
• A Comparison of Deep Learning Models for Proton Background Rejection with the AMS Electromagnetic Calorimeter
• Identifying the Quantum Properties of Hadronic Resonances using Machine Learning
• Jet characterization in Heavy Ion Collisions by QCD-Aware Graph Neural Networks
• Energy Flow in Particle Collisions
• Deep learning for jet modification in the presence of the QGP background
• Vision Transformers for End-to-End Quark-Gluon Jet Classification from Calorimeter Images
• Power Counting Energy Flow Polynomials
• Potential and limitations of machine-learning approaches to inclusive $|V_{ub}|$ determinations
• B-jet Tagging Using a Hybrid Edge Convolution and Transformer Architecture
• New Metric Formulas that Include Measurement Errors in Machine Learning for Natural Sciences
• Exploring an image-based $b$-jet tagging method using convolution neural networks
• Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities