Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bogatskiy, Alexander, Hoffman, Timothy, Miller, David W., Offermann, Jan T., Liu, Xiaoyang
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2307.16506
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929557609644032
author Bogatskiy, Alexander
Hoffman, Timothy
Miller, David W.
Offermann, Jan T.
Liu, Xiaoyang
author_facet Bogatskiy, Alexander
Hoffman, Timothy
Miller, David W.
Offermann, Jan T.
Liu, Xiaoyang
contents PELICAN is a novel permutation equivariant and Lorentz invariant or covariant aggregator network designed to overcome common limitations found in architectures applied to particle physics problems. Compared to many approaches that use non-specialized architectures that neglect underlying physics principles and require very large numbers of parameters, PELICAN employs a fundamentally symmetry group-based architecture that demonstrates benefits in terms of reduced complexity, increased interpretability, and raw performance. We present a comprehensive study of the PELICAN algorithm architecture in the context of both tagging (classification) and reconstructing (regression) Lorentz-boosted top quarks, including the difficult task of specifically identifying and measuring the $W$-boson inside the dense environment of the Lorentz-boosted top-quark hadronic final state. We also extend the application of PELICAN to the tasks of identifying quark-initiated vs.~gluon-initiated jets, and a multi-class identification across five separate target categories of jets. When tested on the standard task of Lorentz-boosted top-quark tagging, PELICAN outperforms existing competitors with much lower model complexity and high sample efficiency. On the less common and more complex task of 4-momentum regression, PELICAN also outperforms hand-crafted, non-machine learning algorithms. We discuss the implications of symmetry-restricted architectures for the wider field of machine learning for physics.
format Preprint
id arxiv_https___arxiv_org_abs_2307_16506
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Explainable Equivariant Neural Networks for Particle Physics: PELICAN
Bogatskiy, Alexander
Hoffman, Timothy
Miller, David W.
Offermann, Jan T.
Liu, Xiaoyang
High Energy Physics - Phenomenology
Machine Learning
High Energy Physics - Experiment
PELICAN is a novel permutation equivariant and Lorentz invariant or covariant aggregator network designed to overcome common limitations found in architectures applied to particle physics problems. Compared to many approaches that use non-specialized architectures that neglect underlying physics principles and require very large numbers of parameters, PELICAN employs a fundamentally symmetry group-based architecture that demonstrates benefits in terms of reduced complexity, increased interpretability, and raw performance. We present a comprehensive study of the PELICAN algorithm architecture in the context of both tagging (classification) and reconstructing (regression) Lorentz-boosted top quarks, including the difficult task of specifically identifying and measuring the $W$-boson inside the dense environment of the Lorentz-boosted top-quark hadronic final state. We also extend the application of PELICAN to the tasks of identifying quark-initiated vs.~gluon-initiated jets, and a multi-class identification across five separate target categories of jets. When tested on the standard task of Lorentz-boosted top-quark tagging, PELICAN outperforms existing competitors with much lower model complexity and high sample efficiency. On the less common and more complex task of 4-momentum regression, PELICAN also outperforms hand-crafted, non-machine learning algorithms. We discuss the implications of symmetry-restricted architectures for the wider field of machine learning for physics.
title Explainable Equivariant Neural Networks for Particle Physics: PELICAN
topic High Energy Physics - Phenomenology
Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2307.16506