Energy flow polynomials: A complete linear basis for jet substructure

Abstract

We introduce the energy flow polynomials: a complete set of jet substructure observables which form a discrete linear basis for all infrared- and collinear-safe observables. Energy flow polynomials are multiparticle energy correlators with specific angular structures that are a direct consequence of infrared and collinear safety. We establish a powerful graph-theoretic representation of the energy flow polynomials which allows us to design efficient algorithms for their computation. Many common jet observables are exact linear combinations of energy flow polynomials, and we demonstrate the linear spanning nature of the energy flow basis by performing regression for several common jet observables. Using linear classification with energy flow polynomials, we achieve excellent performance on three representative jet tagging problems: quark/gluon discrimination, boosted W tagging, and boosted top tagging. The energy flow basis provides a systematic framework for complete investigations of jet substructure using linear methods.

41+15 pages, 13 figures, 5 tables; v2: updated to match JHEP version

References in corpus (25)

• PYTHIA 6.4 Physics and Manual
• An Introduction to PYTHIA 8.2
• Jet substructure as a new Higgs search channel at the LHC
• Conformal collider physics: Energy and charge correlations
• Techniques for improved heavy particle searches with jet substructure
• Classification without labels: Learning from mixed samples in high energy physics
• Strategies to Identify Boosted Tops
• Power Counting to Better Jet Observables
• Gaining (Mutual) Information about Quark/Gluon Discrimination
• Momentum Flow Correlations from Event Shapes: Factorized Soft Gluons and Soft-Collinear Effective Theory
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• New Angles on Energy Correlation Functions
• Sudakov Safety in Perturbative QCD
• Operator bases, $S$-matrices, and their partition functions
• Factorization of e+e- Event Shape Distributions with Hadronic Final States in Soft Collinear Effective Theory
• A generic anti-QCD jet tagger
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Pileup Mitigation with Machine Learning (PUMML)
• Calculating the Charge of a Jet
• Multivariate discrimination and the Higgs + W/Z search
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Resummation of Double-Differential Cross Sections and Fully-Unintegrated Parton Distribution Functions
• Reconstructing Sparticle Mass Spectra using Hadronic Decays
• Precision Jet Substructure from Boosted Event Shapes
• Improved jet substructure methods: Y-splitter and variants with grooming

Cited by in corpus (103)

• Machine learning and the physical sciences
• Energy Flow Networks: Deep Sets for Particle Jets
• The Machine Learning Landscape of Top Taggers
• QCD or What?
• The Collinear Limit of the Energy-Energy Correlator
• Rethinking Jets with Energy Correlators: Tracks, Resummation and Analytic Continuation
• The Lund Jet Plane
• The Metric Space of Collider Events
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• Learning to Classify from Impure Samples with High-Dimensional Data
• Simplicity from Recoil: The Three-Loop Soft Function and Factorization for the Energy-Energy Correlation
• Boosting $H\to b\bar{b}$ with Machine Learning
• Energy-energy correlations at next-to-next-to-leading order
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Exploring the Space of Jets with CMS Open Data
• Fast Point Cloud Generation with Diffusion Models in High Energy Physics
• ABCDisCo: Automating the ABCD Method with Machine Learning
• Higgs Physics: It ain't over till it's over
• An operational definition of quark and gluon jets
• Evaluating generative models in high energy physics
• Deep-Learning Jets with Uncertainties and More
• Casting a graph net to catch dark showers
• Lund jet images from generative and cycle-consistent adversarial networks
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Mapping Machine-Learned Physics into a Human-Readable Space
• Three Point Energy Correlators in the Collinear Limit: Symmetries, Dualities and Analytic Results
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• The Hidden Geometry of Particle Collisions
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Autoencoders for Semivisible Jet Detection
• EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets
• SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• A Theory of Quark vs. Gluon Discrimination
• Equivariant Energy Flow Networks for Jet Tagging
• Symmetries, Safety, and Self-Supervision
• Per-Object Systematics using Deep-Learned Calibration
• Linearized Optimal Transport for Collider Events
• Automating the Construction of Jet Observables with Machine Learning
• The Entropy of a Jet
• Topological Obstructions to Autoencoding
• Deep learning jet modifications in heavy-ion collisions
• Towards Machine Learning Analytics for Jet Substructure
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Computing $N$-subjettiness for boosted jets
• Reports of My Demise Are Greatly Exaggerated: $N$-subjettiness Taggers Take On Jet Images
• Higgs boson tagging with the Lund jet plane
• Three-point energy correlator in $\mathcal{N}=4$ super Yang-Mills Theory
• Calculating the primary Lund Jet Plane density
• Explainable Equivariant Neural Networks for Particle Physics: PELICAN
• What's Anomalous in LHC Jets?
• Spectral Analysis of Jet Substructure with Neural Networks: Boosted Higgs Case
• Machine learning-based jet and event classification at the Electron-Ion Collider with applications to hadron structure and spin physics
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Non-Gaussianities in Collider Energy Flux
• Which Metric on the Space of Collider Events?
• CapsNets Continuing the Convolutional Quest
• Cutting Multiparticle Correlators Down to Size
• Learning to Identify Electrons
• Covariantizing Phase Space
• Leveraging universality of jet taggers through transfer learning
• Resolving Extreme Jet Substructure
• Exploring Jet Substructure in Semi-visible jets
• Learning to Identify Semi-Visible Jets
• Tagging boosted hadronic objects with dynamical grooming
• Jets with electrons from boosted top quarks
• BIP: Boost Invariant Polynomials for Efficient Jet Tagging
• Jet tagging made easy
• Applications of Persistent Homology in Nuclear Collisions
• Systematic Quark/Gluon Identification with Ratios of Likelihoods
• Permutation invariant Gaussian 2-matrix models
• Is infrared-collinear safe information all you need for jet classification?
• New physics with boosted single top production at the LHC and future colliders
• Semi-visible jets, energy-based models, and self-supervision
• Learning to Isolate Muons
• Hypergraphs in LHC Phenomenology -- The Next Frontier of IRC-Safe Feature Extraction
• Accuracy versus precision in boosted top tagging with the ATLAS detector
• Top tagging : an analytical perspective
• Jet Classification Using High-Level Features from Anatomy of Top Jets
• Safe but Incalculable: Energy-weighting is not all you need
• Aspects of Track-Assisted Mass
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• TopicFlow: Disentangling quark and gluon jets with normalizing flows
• Unveiling the Secrets of New Physics Through Top Quark Tagging
• Energy Correlators Beyond Angles
• Investigating top tagging with Y${}_{\text{m}}$-Splitter and N-subjettiness
• Top-philic Machine Learning
• LHC Hadronic Jet Generation Using Convolutional Variational Autoencoders with Normalizing Flows
• Riemannian Data preprocessing in Machine Learning to focus on QCD color structure
• Quark-versus-gluon tagging in CMS Open Data with CWoLa and TopicFlow
• NCoder -- A Quantum Field Theory approach to encoding data
• A method for correcting the substructure of multiprong jets using the Lund jet plane
• Jet Rotational Metrics
• Wasserstein normalized autoencoder for anomaly detection
• Identifying the Quantum Properties of Hadronic Resonances using Machine Learning
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure
• Degeneracy Engineering for Classical and Quantum Annealing: A Case Study of Sparse Linear Regression in Collider Physics
• Graph theory inspired anomaly detection at the LHC
• Reweighting and Analysing Event Generator Systematics by Neural Networks on High-Level Features
• A Field Guide to Event-Shape Observables Using Optimal Transport
• Power Counting Energy Flow Polynomials
• The Physics Behind ML-based Quark-Gluon Taggers
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction