Jet tagging in the Lund plane with graph networks
arXiv:2012.08526
Abstract
The identification of boosted heavy particles such as top quarks or vector bosons is one of the key problems arising in experimental studies at the Large Hadron Collider. In this article, we introduce LundNet, a novel jet tagging method which relies on graph neural networks and an efficient description of the radiation patterns within a jet to optimally disentangle signatures of boosted objects from background events. We apply this framework to a number of different benchmarks, showing significantly improved performance for top tagging compared to existing state-of-the-art algorithms. We study the robustness of the LundNet taggers to non-perturbative and detector effects, and show how kinematic cuts in the Lund plane can mitigate overfitting of the neural network to model-dependent contributions. Finally, we consider the computational complexity of this method and its scaling as a function of kinematic Lund plane cuts, showing an order of magnitude improvement in speed over previous graph-based taggers.
arXiv comment23 pages, 12 figures, code available at https://github.com/fdreyer/lundnet
References in corpus (24)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- An Introduction to PYTHIA 8.2
- DELPHES 3, A modular framework for fast simulation of a generic collider experiment
- Better Jet Clustering Algorithms
- Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
- Towards Jetography
- ParticleNet: Jet Tagging via Particle Clouds
- Energy Correlation Functions for Jet Substructure
- Boosted objects: a probe of beyond the Standard Model physics
- Jet Substructure at the Tevatron and LHC: New results, new tools, new benchmarks
- Quark and Gluon Tagging at the LHC
- Boosted objects and jet substructure at the LHC
- Les Houches 2015: Physics at TeV Colliders Standard Model Working Group Report
- Parton showers beyond leading logarithmic accuracy
- On the Topic of Jets: Disentangling Quarks and Gluons at Colliders
- Novel Jet Observables from Machine Learning
- Probing stop pair production at the LHC with graph neural networks
- Measurement of the Lund jet plane using charged particles in 13 TeV proton-proton collisions with the ATLAS detector
- Unveiling CP property of top-Higgs coupling with graph neural networks at the LHC
- Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
- Equivariant Energy Flow Networks for Jet Tagging
- Jet grooming through reinforcement learning
- Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation