How Much Information is in a Jet?

Abstract

Machine learning techniques are increasingly being applied toward data analyses at the Large Hadron Collider, especially with applications for discrimination of jets with different originating particles. Previous studies of the power of machine learning to jet physics has typically employed image recognition, natural language processing, or other algorithms that have been extensively developed in computer science. While these studies have demonstrated impressive discrimination power, often exceeding that of widely-used observables, they have been formulated in a non-constructive manner and it is not clear what additional information the machines are learning. In this paper, we study machine learning for jet physics constructively, expressing all of the information in a jet onto sets of observables that completely and minimally span N-body phase space. For concreteness, we study the application of machine learning for discrimination of boosted, hadronic decays of Z bosons from jets initiated by QCD processes. Our results demonstrate that the information in a jet that is useful for discrimination power of QCD jets from Z bosons is saturated by only considering observables that are sensitive to 4-body (8 dimensional) phase space.

14 pages + appendices, 10 figures; v2: JHEP version, updated neural network, included deeper network and boosted decision tree results

References in corpus (15)

• PYTHIA 6.4 Physics and Manual
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• An Introduction to PYTHIA 8.2
• Herwig++ Physics and Manual
• Boosted objects: a probe of beyond the Standard Model physics
• Deep learning in color: towards automated quark/gluon jet discrimination
• Deep-learning Top Taggers or The End of QCD?
• Power Counting to Better Jet Observables
• Gaining (Mutual) Information about Quark/Gluon Discrimination
• New Angles on Energy Correlation Functions
• Light-quark and gluon jet discrimination in pp collisions at $\sqrt{s}$ = 7 TeV with the ATLAS detector
• Resummation of Double-Differential Cross Sections and Fully-Unintegrated Parton Distribution Functions
• Weakly Supervised Classification in High Energy Physics
• Dichroic subjettiness ratios to distinguish colour flows in boosted boson tagging
• A New Observable for Identifying Dijet Resonances

Cited by in corpus (74)

• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Classification without labels: Learning from mixed samples in high energy physics
• Searching for New Physics with Deep Autoencoders
• Energy Flow Networks: Deep Sets for Particle Jets
• The Machine Learning Landscape of Top Taggers
• Learning New Physics from a Machine
• Extending the Bump Hunt with Machine Learning
• Deep-learned Top Tagging with a Lorentz Layer
• A generic anti-QCD jet tagger
• QCD or What?
• What is the Machine Learning?
• Energy flow polynomials: A complete linear basis for jet substructure
• The Lund Jet Plane
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Uncovering latent jet substructure
• Learning to Classify from Impure Samples with High-Dimensional Data
• Boosting $H\to b\bar{b}$ with Machine Learning
• Recursive Neural Networks in Quark/Gluon Tagging
• Novel Jet Observables from Machine Learning
• (Machine) Learning to Do More with Less
• ABCDisCo: Automating the ABCD Method with Machine Learning
• Quark-Gluon Tagging: Machine Learning vs Detector
• An operational definition of quark and gluon jets
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Deep-Learning Jets with Uncertainties and More
• Supervised deep learning in high energy phenomenology: a mini review
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Mapping Machine-Learned Physics into a Human-Readable Space
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• The Hidden Geometry of Particle Collisions
• A Theory of Quark vs. Gluon Discrimination
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Mass Unspecific Supervised Tagging (MUST) for boosted jets
• Per-Object Systematics using Deep-Learned Calibration
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Automating the Construction of Jet Observables with Machine Learning
• The Entropy of a Jet
• Topological Obstructions to Autoencoding
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Deep learning jet modifications in heavy-ion collisions
• Mass Agnostic Jet Taggers
• Towards Machine Learning Analytics for Jet Substructure
• 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
• 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
• Stealth multiboson signals
• Anomaly detection from mass unspecific jet tagging
• Deep learning for the R-parity violating supersymmetry searches at the LHC
• CapsNets Continuing the Convolutional Quest
• Jet grooming through reinforcement learning
• The importance of calorimetry for highly-boosted jet substructure
• A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
• Leading jets and energy loss
• Invisible Higgs search through Vector Boson Fusion: A deep learning approach
• Resolving Extreme Jet Substructure
• Taming modeling uncertainties with Mass Unspecific Supervised Tagging
• The minimal stealth boson: models and benchmarks
• Maximum performance of strange-jet tagging at hadron colliders
• Jet tagging made easy
• Is infrared-collinear safe information all you need for jet classification?
• Beyond $M_{t\bar{t}}$: learning to search for a broad $t\bar{t}$ resonance at the LHC
• Jet Classification Using High-Level Features from Anatomy of Top Jets
• Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation
• Top-philic Machine Learning
• How much joint resummation do we need?
• Identifying the Quantum Properties of Hadronic Resonances using Machine Learning
• Graph theory inspired anomaly detection at the LHC
• Learnable cut flow for high energy physics
• Machine learning tagged boosted dark photon: A signature of fermionic portal matter at the LHC
• Power Counting Energy Flow Polynomials
• Pulling the Higgs and Top needles from the jet stack with Feature Extended Supervised Tagging