Fetching the paper…

Reading the bibliography…

2023

Explainable Equivariant Neural Networks for Particle Physics: PELICAN

Bogatskiy, Alexander, Hoffman, Timothy, Miller, David W. et al.

Original
PDF
Post on X

Understand

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.

Explainable Equivariant Neural Networks for Particle Physics: PELICAN · Around

Built on

S. Marzani, G. Soyez and M. Spannowsky, Looking inside jets: an introduction to jet substructure and boosted-object phenomenology , vol. 958, Springer (2019), 10.1007/978-3-030-15709-8 , [ 1901.10342 ]
Original
1901
Earlier work this paper cites.
G. Kasieczka, T. Plehn, A. Butter, K. Cranmer, D. Debnath, B.M. Dillon et al., The Machine Learning landscape of top taggers , SciPost Phys. 7
Original
1902
Earlier work this paper cites.
A. Sannai, Y. Takai and M. Cordonnier, Universal approximations of permutation invariant/equivariant functions by deep neural networks , Preprint (2019) [ 1903.01939 ]
Original
1903
Earlier work this paper cites.
H. Weyl, The Classical Groups. Their Invariants and Representations , Princeton University Press, Princeton, N.J., 2 ed. (1946)
1946
Earlier work this paper cites.
Y. Dokshitzer, G. Leder, S. Moretti and B. Webber, Better jet clustering algorithms , JHEP 1997
1997
Earlier work this paper cites.
M. Wobisch and T. Wengler, Hadronization corrections to jet cross sections in deep-inelastic scattering , in Proceedings, Workshop, Hamburg, Germany, 1998-1999 , p. 270–279, 1999 [ hep-ph/9907280 ]
1999
Earlier work this paper cites.
G. Corso et al., Principal neighbourhood aggregation for graph nets , in NeurIPS , vol. 33, pp. 13260–13271, Curran, 2020, https://proceedings.neurips.cc/paper/2020/file/99cad265a1768cc2dd013f0e740300ae-Paper.pdf [ 2004.05718 ]
Original
2004
Earlier work this paper cites.
A. Bogatskiy, B.M. Anderson, J.T. Offermann, M. Roussi, D.W. Miller and R. Kondor, Lorentz group equivariant neural network for particle physics , in ICML 2020 , vol. 119 of PMLR , pp. 992–1002, PMLR, 2020, http://proceedings.mlr.press/v119/bogatskiy20a.html [ 2006.04780 ]
Original
2006
Earlier work this paper cites.
W. Azizian and M. Lelarge, Expressive power of invariant and equivariant graph neural networks , in ICLR 2021 , OpenReview, 2021, https://openreview.net/forum?id=lxHgXYN4bwl [ 2006.15646 ]
Original
2006
Earlier work this paper cites.
J.M. Butterworth, A.R. Davison, M. Rubin and G.P. Salam, Jet substructure as a new Higgs search channel at the LHC , Phys. Rev. Lett. 100
Original
2008
Earlier work this paper cites.
D.E. Kaplan, K. Rehermann, M.D. Schwartz and B. Tweedie, Top Tagging: A Method for Identifying Boosted Hadronically Decaying Top Quarks , Phys. Rev. Lett. 101
Original
2008
Earlier work this paper cites.
J. Thaler and L.-T. Wang, Strategies to identify boosted tops , JHEP 07
Original
2008
Earlier work this paper cites.
M. Cacciari, G.P. Salam and G. Soyez, The anti- k t k_{t} jet clustering algorithm , JHEP 04
Original
2008
Earlier work this paper cites.
N. Dym and H. Maron, On the universality of rotation equivariant point cloud networks , in ICLR 2021 , OpenReview, 2021, https://openreview.net/forum?id=6NFBvWlRXaG [ 2010.02449 ]
Original
2010
Earlier work this paper cites.
J. Thaler and K. Van Tilburg, Identifying Boosted Objects with N-subjettiness , JHEP 03
Original
2011
Earlier work this paper cites.
I. Feige, M.D. Schwartz, I.W. Stewart and J. Thaler, Precision Jet Substructure from Boosted Event Shapes , Phys. Rev. Lett. 109
Original
2012
Earlier work this paper cites.
M. Cacciari, G.P. Salam and G. Soyez, FastJet User Manual , Eur. Phys. J. C 72
Original
2012
Earlier work this paper cites.
J. Gallicchio and M.D. Schwartz, Quark and gluon jet substructure , JHEP 2013
Original
2013
Earlier work this paper cites.
D.E. Soper and M. Spannowsky, Finding top quarks with shower deconstruction , Phys. Rev. D 87
Original
2013
Earlier work this paper cites.
A.J. Larkoski, J. Thaler and W.J. Waalewijn, Gaining (Mutual) Information about Quark/Gluon Discrimination , JHEP 11
Original
2014
Earlier work this paper cites.
Y.-T. Chien and I. Vitev, Jet Shape Resummation Using Soft-Collinear Effective Theory , JHEP 12
Original
2014
Earlier work this paper cites.
DELPHES 3
Original
2014
Earlier work this paper cites.
T. Chen and C. Guestrin, XGBoost: A scalable tree boosting system , in Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. 22 , B. Krishnapuram, M. Shah, A.J. Smola, C.C. Aggarwal, D. Shen and R. Rastogi, eds., pp. 785–794, ACM, 2016, DOI
2016
Earlier work this paper cites.
P.T. Komiske, E.M. Metodiev and M.D. Schwartz, Deep learning in color: towards automated quark/gluon jet discrimination , JHEP 01
Original
2017
Earlier work this paper cites.

Similar

M. Zaheer, S. Kottur, S. Ravanbakhsh, B. Poczos, R.R. Salakhutdinov and A.J. Smola, Deep Sets , in Adv. Neural Inf. Process. 30 , I. Guyon, U.V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan et al., eds., pp. 3391–3401, Curran Associates, Inc. (2017), http://papers.nips.cc/paper/6931-deep-sets.pdf
2017
Cited alongside, same era.
C. Frye, A.J. Larkoski, J. Thaler and K. Zhou, Casimir Meets Poisson: Improved Quark/Gluon Discrimination with Counting Observables , JHEP 09
Original
2017
Cited alongside, same era.
S. Marzani, L. Schunk and G. Soyez, The jet mass distribution after Soft Drop , Eur. Phys. J. C 78
Original
2018
Cited alongside, same era.
F.A. Dreyer, G.P. Salam and G. Soyez, The Lund Jet Plane , JHEP 12
Original
2018
Cited alongside, same era.

Then

B. Gripaios, W. Haddadin and C.G. Lester, Lorentz- and permutation-invariants of particles , J. Phys. A Math. Theor. 54
2021
Later among the works it cites.
S. Villar, D.W. Hogg, K. Storey-Fisher, W. Yao and B. Blum-Smith, Scalars are universal: Equivariant machine learning, structured like classical physics , in Adv. Neural Inf. Process. 34 , M. Ranzato, A. Beygelzimer, Y.N. Dauphin, P. Liang and J.W. Vaughan, eds., pp. 28848–28863, 2021, https://proceedings.neurips.cc/paper/2021/hash/f1b0775946bc0329b35b823b86eeb5f5-Abstract.html [ 2106.06610 ]
Original
2021
Later among the works it cites.
V. Mikuni and F. Canelli, Point cloud transformers applied to collider physics , Machine Learning: Science and Technology 2
2021
Later among the works it cites.
E. Alvarez, M. Spannowsky and M. Szewc, Unsupervised quark/gluon jet tagging with poissonian mixture models , Front. Artif. Intell. 5
2022
Later among the works it cites.
S. Gong, Q. Meng, J. Zhang, H. Qu, C. Li, S. Qian et al., An efficient lorentz equivariant graph neural network for jet tagging , JHEP 2022

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

P.T. Komiske, E.M. Metodiev and J. Thaler, Energy flow polynomials: A complete linear basis for jet substructure , JHEP 04

Original

2018

Cited alongside, same era.

A. Butter, G. Kasieczka, T. Plehn and M. Russell, Deep-learned Top Tagging with a Lorentz Layer , SciPost Phys. 5

2018

Cited alongside, same era.

J. Duarte, S. Han, P. Harris, S. Jindariani, E. Kreinar, B. Kreis et al., Fast inference of deep neural networks in FPGAs for particle physics , Journal of Instrumentation 13

2018

Cited alongside, same era.

G. Kasieczka, N. Kiefer, T. Plehn and J.M. Thompson, Quark-gluon tagging: Machine learning vs detector , SciPost Phys. 6

2019

Cited alongside, same era.

R. Kogler et al., Jet Substructure at the Large Hadron Collider: Experimental Review , Rev. Mod. Phys. 91

2019

Cited alongside, same era.

M. Erdmann, E. Geiser, Y. Rath and M. Rieger, Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering , JINST 14

2019

Cited alongside, same era.

P.T. Komiske, E.M. Metodiev and J. Thaler, Energy flow networks: deep sets for particle jets , JHEP 2019

2019

Cited alongside, same era.

H. Maron, H. Ben-Hamu, N. Shamir and Y. Lipman, Invariant and equivariant graph networks , in ICLR 2019 , OpenReview, 2019, https://openreview.net/forum?id=Syx72jC9tm [ 1812.09902 ]

2019

Cited alongside, same era.

2022

Later among the works it cites.

A. Bogatskiy et al., Symmetry Group Equivariant Architectures for Physics , in Snowmass 2021 , 3, 2022 [ 2203.06153 ]

2022

Later among the works it cites.

E. Wagstaff, F.B. Fuchs, M. Engelcke, M.A. Osborne and I. Posner, Universal approximation of functions on sets , J. Mach. Learn. Res. 23

2022

Later among the works it cites.

H. Qu, C. Li and S. Qian, Particle transformer for jet tagging , in ICML 2022 , K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvári, G. Niu and S. Sabato, eds., vol. 162 of PMLR , pp. 18281–18292, PMLR, 2022, https://proceedings.mlr.press/v162/qu22b.html [ 2202.03772 ]

2022

Later among the works it cites.

H. Pan and R. Kondor, Permutation equivariant layers for higher order interactions , in AISTATS , pp. 5987–6001, PMLR, 28–30 Mar, 2022, https://proceedings.mlr.press/v151/pan22a.html

2022

Later among the works it cites.

C. Bierlich et al., A comprehensive guide to the physics and usage of PYTHIA 8.3 , SciPost Phys. Codeb. 2022

2022

Later among the works it cites.

J.M. Munoz, I. Batatia and C. Ortner, Boost invariant polynomials for efficient jet tagging , Machine Learning: Science and Technology 3

2022

Later among the works it cites.

R. Das, G. Kasieczka and D. Shih, Feature selection with distance correlation , Preprint (2022) [ 2212.00046 ]

Original

2022

Later among the works it cites.

P. Konar, V.S. Ngairangbam and M. Spannowsky, Energy-weighted message passing: an infra-red and collinear safe graph neural network algorithm , JHEP 2022

2022

Later among the works it cites.

Particle Data Group

2022

Later among the works it cites.

HEP ML Community, A Living Review of Machine Learning for Particle Physics , GitHub (2023)

2023

Closest in time.

J.T. Offermann, T. Hoffman and A. Bogatskiy, Top Jet W-Momentum Reconstruction Dataset , Zenodo 1.0.0

2023

Closest in time.

E. Witkowski and D. Whiteson, Learning broken symmetries with resimulation and encouraged invariance , Preprint (2023) [ 2311.05952 ]

2023

Closest in time.

S. Qiu, S. Han, X. Ju, B. Nachman and H. Wang, Holistic approach to predicting top quark kinematic properties with the covariant particle transformer , Phys. Rev. D 107

2023

Closest in time.

T. Sun, A. Hands and R. Kondor, P-tensors: a General Formalism for Constructing Higher Order Message Passing Networks , Preprint (2023) [ 2306.10767 ]

2023

Closest in time.

M. Pierini, J.M. Duarte, N. Tran, M. Freytsis and A. Bogatskiy, Converted HLS4ML LHC Jet Dataset (100 particles) , OSF Dataset v1

2023

Closest in time.

J.T. Offermann, X. Liu and T. Hoffman, HEPData4ML , GitHub (2023)

2023

Closest in time.

S. Qiu, S. Han, X. Ju, B. Nachman and H. Wang, Parton labeling without matching: unveiling emergent labelling capabilities in regression models , The European Physical Journal C 83

2023

Closest in time.

D. Athanasakos, A.J. Larkoski, J. Mulligan, M. Ploskon and F. Ringer, Is infrared-collinear safe information all you need for jet classification? , Preprint (2023) [ 2305.08979 ]

2023

Closest in time.