Deep Learning Jet Substructure from Two-Particle Correlation

Abstract

Deciphering the complex information contained in jets produced in collider events requires a physical organization of the jet data. We introduce two-particle correlations (2PCs) by pairing individual particles as the initial jet representation from which a probabilistic model can be built. Particle momenta, as well as particle types and vertex information are included in the correlation. A novel, two-particle correlation neural network (2PCNN) architecture is constructed by combining neural network based filters on 2PCs and a deep neural network for capturing jet kinematic information. The 2PCNN is applied to boosted boson and heavy flavor tagging, and it achieves excellent performance by comparing to models based on telescoping deconstruction. Major correlation pairs exploited in the trained models are also identified, which shed light on the physical significance of certain jet substructure.

arXiv comment5 pages, 4 figures, example code and test sample available at github.com/kfjack/2PCNN

References in corpus (35)

• 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
• A Brief Introduction to PYTHIA 8.1
• FastJet user manual
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Soft Drop
• Towards an understanding of jet substructure
• ParticleNet: Jet Tagging via Particle Clouds
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Jet-Images -- Deep Learning Edition
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Deep-learning Top Taggers or The End of QCD?
• Searching for New Physics with Deep Autoencoders
• Anomaly Detection for Resonant New Physics with Machine Learning
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Energy Flow Networks: Deep Sets for Particle Jets
• Deep-learned Top Tagging with a Lorentz Layer
• How to GAN LHC Events
• OmniFold: A Method to Simultaneously Unfold All Observables
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Pulling Out All the Tops with Computer Vision and Deep Learning
• QCD-Aware Recursive Neural Networks for Jet Physics
• Pileup Mitigation with Machine Learning (PUMML)
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Boosting $H\to b\bar{b}$ with Machine Learning
• Recursive Neural Networks in Quark/Gluon Tagging
• Jet Charge and Machine Learning
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Boosted $W/Z$ Tagging with Jet Charge and Deep Learning
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• Spectral Analysis of Jet Substructure with Neural Networks: Boosted Higgs Case
• Collinear Drop
• Telescoping Jets: Multiple Event Interpretations with Multiple R's
• Quantifying the power of multiple event interpretations

Cited by in corpus (5)

• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Deep learning assisted jet tomography for the study of Mach cones in QGP
• Probing hadronization with flavor correlations of leading particles in jets
• Jet Discrimination with Quantum Complete Graph Neural Network
• Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation