Equivariant Energy Flow Networks for Jet Tagging

Abstract

Jet tagging techniques that make use of deep learning show great potential for improving physics analyses at colliders. One such method is the Energy Flow Network (EFN) - a recently introduced neural network architecture that represents jets as permutation-invariant sets of particle momenta while maintaining infrared and collinear safety. We develop a variant of the Energy Flow Network architecture based on the Deep Sets formalism, incorporating permutation-equivariant layers. We derive conditions under which infrared and collinear safety can be maintained, and study the performance of these networks on the canonical example of W-boson tagging. We find that equivariant Energy Flow Networks have similar performance to Particle Flow Networks, which are superior to standard EFNs. However, equivariant Particle Flow Networks suffer from convergence and overfitting issues. Finally, we study how equivariant networks sculpt the jet mass and provide some initial results on decorrelation using planing.

arXiv comment20 pages, 8 figures

References in corpus (61)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Jet substructure as a new Higgs search channel at the LHC
• Identifying Boosted Objects with N-subjettiness
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Towards Jetography
• ParticleNet: Jet Tagging via Particle Clouds
• Jet substructure as a new Higgs search channel at the LHC
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Searching for New Physics with Deep Autoencoders
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Energy Flow Networks: Deep Sets for Particle Jets
• Quark and Gluon Tagging at the LHC
• Deep-learned Top Tagging with a Lorentz Layer
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• QCD or What?
• A generic anti-QCD jet tagger
• Quark and Gluon Jet Substructure
• What is the Machine Learning?
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Energy flow polynomials: A complete linear basis for jet substructure
• Top Tagging
• Pulling Out All the Tops with Computer Vision and Deep Learning
• The Lund Jet Plane
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• JEDI-net: a jet identification algorithm based on interaction networks
• QCD-Aware Recursive Neural Networks for Jet Physics
• Casimir Meets Poisson: Improved Quark/Gluon Discrimination with Counting Observables
• Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
• Recursive Neural Networks in Quark/Gluon Tagging
• Deep Sets
• DisCo Fever: Robust Networks Through Distance Correlation
• Lorentz Group Equivariant Neural Network for Particle Physics
• Quark-Gluon Tagging: Machine Learning vs Detector
• Unveiling CP property of top-Higgs coupling with graph neural networks at the LHC
• Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
• An operational definition of quark and gluon jets
• Quark-Gluon tagging with Shower Deconstruction: Unearthing dark matter and Higgs couplings
• On jet substructure methods for signal jets
• Mapping Machine-Learned Physics into a Human-Readable Space
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• A Theory of Quark vs. Gluon Discrimination
• uBoost: A boosting method for producing uniform selection efficiencies from multivariate classifiers
• Mass Unspecific Supervised Tagging (MUST) for boosted jets
• Convolved Substructure: Analytically Decorrelating Jet Substructure Observables
• Mass Agnostic Jet Taggers
• Jet Constituents for Deep Neural Network Based Top Quark Tagging
• Towards Machine Learning Analytics for Jet Substructure
• Probing triple Higgs coupling with machine learning at the LHC
• Fractal based observables to probe jet substructure of quarks and gluons
• BRUNO: A Deep Recurrent Model for Exchangeable Data
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
• Learning Functions over Sets via Permutation Adversarial Networks

Cited by in corpus (25)

• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Jet Flavour Tagging for Future Colliders with Fast Simulation
• SymmetryGAN: Symmetry Discovery with Deep Learning
• Explainable machine learning of the underlying physics of high-energy particle collisions
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• IRC-safe Graph Autoencoder for unsupervised anomaly detection
• Unbinned Deep Learning Jet Substructure Measurement in High $Q^2$ ep collisions at HERA
• Jet tagging algorithm of graph network with HaarPooling message passing
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• Jet Discrimination with Quantum Complete Graph Neural Network
• Comparing Point Cloud Strategies for Collider Event Classification
• Meta-learning and data augmentation for mass-generalised jet taggers
• A rotation-equivariant graph neural network for learning hadronic SMEFT effects
• ${\mathbb{Z}}_2\times {\mathbb{Z}}_2$ Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks
• Jet tagging in the Lund plane with graph networks
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Top-philic Machine Learning
• Equivariant neural networks for robust $\text{CP}$ observables
• Event Generation and Density Estimation with Surjective Normalizing Flows
• Identifying the Quantum Properties of Hadronic Resonances using Machine Learning
• Learnable cut flow for high energy physics
• Deep learning for jet modification in the presence of the QGP background
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction