SciPost: SciPost Phys. 7, 014 (2019) - The Machine Learning landscape of top taggers

SciPost Physics

The Machine Learning landscape of top taggers

Gregor Kasieczka, Tilman Plehn, Anja Butter, Kyle Cranmer, Dipsikha Debnath, Barry M. Dillon, Malcolm Fairbairn, Darius A. Faroughy, Wojtek Fedorko, Christophe Gay, Loukas Gouskos, Jernej F. Kamenik, Patrick T. Komiske, Simon Leiss, Alison Lister, Sebastian Macaluso, Eric M. Metodiev, Liam Moore, Ben Nachman, Karl Nordström, Jannicke Pearkes, Huilin Qu, Yannik Rath, Marcel Rieger, David Shih, Jennifer M. Thompson, Sreedevi Varma

SciPost Phys. 7, 014 (2019) · published 30 July 2019

doi: 10.21468/SciPostPhys.7.1.014
pdf
Submissions/Reports

Abstract

Based on the established task of identifying boosted, hadronically decaying top quarks, we compare a wide range of modern machine learning approaches. Unlike most established methods they rely on low-level input, for instance calorimeter output. While their network architectures are vastly different, their performance is comparatively similar. In general, we find that these new approaches are extremely powerful and great fun.

TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.7.1.014
TI  - The Machine Learning landscape of top taggers
PY  - 2019/07/30
UR  - https://scipost.org/SciPostPhys.7.1.014
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 7
IS  - 1
SP  - 014
A1  - Kasieczka, Gregor
AU  - Plehn, Tilman
AU  - Butter, Anja
AU  - Cranmer, Kyle
AU  - Debnath, Dipsikha
AU  - Dillon, Barry M.
AU  - Fairbairn, Malcolm
AU  - Faroughy, Darius A.
AU  - Fedorko, Wojtek
AU  - Gay, Christophe
AU  - Gouskos, Loukas
AU  - F. Kamenik, Jernej
AU  - Komiske, Patrick
AU  - Leiss, Simon
AU  - Lister, Alison
AU  - Macaluso, Sebastian
AU  - Metodiev, Eric
AU  - Moore, Liam
AU  - Nachman, Benjamin
AU  - Nordström, Karl
AU  - Pearkes, Jannicke
AU  - Qu, Huilin
AU  - Rath, Yannik
AU  - Rieger, Marcel
AU  - Shih, David
AU  - Thompson, Jennifer
AU  - Varma, Sreedevi
AB  - Based on the established task of identifying boosted, hadronically decaying top quarks, we compare a wide range of modern machine learning approaches. Unlike most established methods they rely on low-level input, for instance calorimeter output. While their network architectures are vastly different, their performance is comparatively similar. In general, we find that these new approaches are extremely powerful and great fun.
ER  -

@Article{10.21468/SciPostPhys.7.1.014,
	title={{The Machine Learning landscape of top taggers}},
	author={Gregor Kasieczka and Tilman Plehn and Anja Butter and Kyle Cranmer and Dipsikha Debnath and Barry M. Dillon and Malcolm Fairbairn and Darius A. Faroughy and Wojtek Fedorko and Christophe Gay and Loukas Gouskos and Jernej F. Kamenik and Patrick T. Komiske and Simon Leiss and Alison Lister and Sebastian Macaluso and Eric M. Metodiev and Liam Moore and Ben Nachman and Karl Nordström and Jannicke Pearkes and Huilin Qu and Yannik Rath and Marcel Rieger and David Shih and Jennifer M. Thompson and Sreedevi Varma},
	journal={SciPost Phys.},
	volume={7},
	pages={014},
	year={2019},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.7.1.014},
	url={https://scipost.org/10.21468/SciPostPhys.7.1.014},
}

Cited by 132

Bogatskiy et al., Explainable equivariant neural networks for particle physics: PELICAN
J. High Energ. Phys. 2024, 113 (2024) [Crossref]
Vigl et al., Finetuning foundation models for joint analysis optimization in High Energy Physics
Mach. Learn.: Sci. Technol. 5, 025075 (2024) [Crossref]
Mondal et al., Machine learning in high energy physics: a review of heavy-flavor jet tagging at the LHC
Eur. Phys. J. Spec. Top., (2024) [Crossref]
Dillon et al., Learning Latent Jet Structure
Symmetry 13, 1167 (2021) [Crossref]
Yang et al., Search for single vector-like B quark production in hadronic final states at the LHC
Eur. Phys. J. C 84, 1124 (2024) [Crossref]
Bister et al., Identification of patterns in cosmic-ray arrival directions using dynamic graph convolutional neural networks
Astroparticle Physics 126, 102527 102527 (2021) [Crossref]
Bernreuther et al., Casting a graph net to catch dark showers
SciPost Phys. 10, 046 (2021) [Crossref]
Araz et al., Combine and conquer: event reconstruction with Bayesian Ensemble Neural Networks
J. High Energ. Phys. 2021, 296 (2021) [Crossref]
Konar et al., Energy-weighted message passing: an infra-red and collinear safe graph neural network algorithm
J. High Energ. Phys. 2022, 60 (2022) [Crossref]
Dillon et al., Anomalies, representations, and self-supervision
SciPost Phys. Core 7, 056 (2024) [Crossref]
Murnane et al., Semi-Equivariant GNN Architectures for Jet Tagging
J. Phys.: Conf. Ser. 2438, 012121 (2023) [Crossref]
Anzalone et al., Triggering dark showers with conditional dual auto-encoders
Mach. Learn.: Sci. Technol. 5, 035064 (2024) [Crossref]
Capozi et al., Exploring anomalous couplings in Higgs boson pair production through shape analysis
J. High Energ. Phys. 2020, 91 (2020) [Crossref]
Bright-Thonney et al., Infrared-safe energy weighting does not guarantee small nonperturbative effects
Phys. Rev. D 110, 014029 (2024) [Crossref]
Chang et al., Distinguishing W′ signals at hadron colliders using neural networks
Phys. Rev. D 103, 036016 (2021) [Crossref]
Chakraborty et al., Tagging a boosted top quark with a τ final state
Phys. Rev. D 108, 035011 (2023) [Crossref]
Zhang et al., Machine learning topological invariants of non-Hermitian systems
Phys. Rev. A 103, 012419 (2021) [Crossref]
Stielow et al., Reconstruction of nanoscale particles from single-shot wide-angle free-electron-laser diffraction patterns with physics-informed neural networks
Phys. Rev. E 103, 053312 (2021) [Crossref]
Finke et al., Learning the language of QCD jets with transformers
J. High Energ. Phys. 2023, 184 (2023) [Crossref]
Qu et al., Jet tagging via particle clouds
Phys. Rev. D 101, 056019 (2020) [Crossref]
Flacke et al., Uncovering doubly charged scalars with dominant three-body decays using machine learning
J. High Energ. Phys. 2023, 9 (2023) [Crossref]
Kasieczka et al., Automating the ABCD method with machine learning
Phys. Rev. D 103, 035021 (2021) [Crossref]
Gambhir et al., Streamlining latent spaces in machine learning using moment pooling
Phys. Rev. D 110, 074020 (2024) [Crossref]
Furuichi et al., Jet classification using high-level features from anatomy of top jets
J. High Energ. Phys. 2024, 146 (2024) [Crossref]
Cal et al., Power counting energy flow polynomials
J. High Energ. Phys. 2022, 21 (2022) [Crossref]
Chien et al., Jet angularities in dijet production in proton-proton and heavy-ion collisions at RHIC
J. High Energ. Phys. 2024, 230 (2024) [Crossref]
Araz et al., Searches for new physics with boosted top quarks in the MadAnalysis 5 and Rivet frameworks
Eur. Phys. J. C 83, 664 (2023) [Crossref]
Nachman, A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
SciPost Phys. 8, 090 (2020) [Crossref]
Athanasakos et al., Is infrared-collinear safe information all you need for jet classification?
J. High Energ. Phys. 2024, 257 (2024) [Crossref]
Faucett et al., Mapping machine-learned physics into a human-readable space
Phys. Rev. D 103, 036020 (2021) [Crossref]
Ruiz-Gándara et al., Generative Adversarial Networks in Business and Social Science
Applied Sciences 14, 7438 (2024) [Crossref]
Dillon et al., A normalized autoencoder for LHC triggers
SciPost Phys. Core 6, 074 (2023) [Crossref]
Birk et al., OmniJet-α: the first cross-task foundation model for particle physics
Mach. Learn.: Sci. Technol. 5, 035031 (2024) [Crossref]
Thaprasop et al., Unsupervised outlier detection in heavy-ion collisions
Phys. Scr. 96, 064003 (2021) [Crossref]
Bierlich et al., Robust Independent Validation of Experiment and Theory: Rivet version 3
SciPost Phys. 8, 026 (2020) [Crossref]
Moreno et al., JEDI-net: a jet identification algorithm based on interaction networks
Eur. Phys. J. C 80, 58 (2020) [Crossref]
Beauchesne et al., Improving the performance of weak supervision searches using transfer and meta-learning
J. High Energ. Phys. 2024, 138 (2024) [Crossref]
Karagiorgi et al., Machine learning in the search for new fundamental physics
Nat Rev Phys 4, 399 (2022) [Crossref]
Alimena et al., Fast convolutional neural networks for identifying long-lived particles in a high-granularity calorimeter
J. Inst. 15, P12006 (2020) [Crossref]
Xuan et al.,
13715, 51 (2023) [Crossref]
Romero et al., Jet rotational metrics
J. High Energ. Phys. 2024, 49 (2024) [Crossref]
Wang et al., Continuous-Mixture Autoregressive Networks Learning the Kosterlitz-Thouless Transition
Chinese Phys. Lett. 39, 120502 (2022) [Crossref]
Buss et al., What's anomalous in LHC jets?
SciPost Phys. 15, 168 (2023) [Crossref]
Odagiu et al., Ultrafast jet classification at the HL-LHC
Mach. Learn.: Sci. Technol. 5, 035017 (2024) [Crossref]
Andrews et al., End-to-end jet classification of quarks and gluons with the CMS Open Data
Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 977, 164304 164304 (2020) [Crossref]
Huang et al., Heterogeneous Graph Neural Network for identifying hadronically decayed tau leptons at the High Luminosity LHC
J. Inst. 18, P07001 (2023) [Crossref]
Sahu et al., Unveiling the secrets of new physics through top quark tagging
Eur. Phys. J. Spec. Top., (2024) [Crossref]
Larkoski, Binary discrimination through next-to-leading order
J. High Energ. Phys. 2024, 57 (2024) [Crossref]
Alvarez et al., Exploring unsupervised top tagging using Bayesian inference
SciPost Phys. Core 6, 046 (2023) [Crossref]
Andrews et al., End-to-end jet classification of boosted top quarks with the CMS open data
Phys. Rev. D 105, 052008 (2022) [Crossref]
Arratia et al., Reconstructing the kinematics of deep inelastic scattering with deep learning
Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 1025, 166164 166164 (2022) [Crossref]
Onyisi et al., Comparing point cloud strategies for collider event classification
Phys. Rev. D 108, 012001 (2023) [Crossref]
Butter et al., Performance versus resilience in modern quark-gluon tagging
SciPost Phys. Core 6, 085 (2023) [Crossref]
Bollweg et al., Deep-learning jets with uncertainties and more
SciPost Phys. 8, 006 (2020) [Crossref]
Kuttan et al., Deep Learning Based Impact Parameter Determination for the CBM Experiment
Particles 4, 47 (2021) [Crossref]
Albouy et al., Theory, phenomenology, and experimental avenues for dark showers: a Snowmass 2021 report
Eur. Phys. J. C 82, 1132 (2022) [Crossref]
Komiske et al., Cutting multiparticle correlators down to size
Phys. Rev. D 101, 036019 (2020) [Crossref]
Kasieczka et al., Per-object systematics using deep-learned calibration
SciPost Phys. 9, 089 (2020) [Crossref]
Baldi et al., How to GAN Higher Jet Resolution
SciPost Phys. 13, 064 (2022) [Crossref]
Araz et al., Classical versus quantum: Comparing tensor-network-based quantum circuits on Large Hadron Collider data
Phys. Rev. A 106, 062423 (2022) [Crossref]
Pol et al., Lightweight jet reconstruction and identification as an object detection task
Mach. Learn.: Sci. Technol. 3, 025016 (2022) [Crossref]
Benato et al., Teaching machine learning with an application in collider particle physics
J. Inst. 15, C09011 (2020) [Crossref]
Campos et al., End-to-end codesign of Hessian-aware quantized neural networks for FPGAs
ACM Trans. Reconfigurable Technol. Syst. 17, 1 (2024) [Crossref]
Goodsell et al., Active learning BSM parameter spaces
Eur. Phys. J. C 83, 268 (2023) [Crossref]
Bradshaw et al., Mass agnostic jet taggers
SciPost Phys. 8, 011 (2020) [Crossref]
Aad et al., Accuracy versus precision in boosted top tagging with the ATLAS detector
J. Inst. 19, P08018 (2024) [Crossref]
Mikuni et al., Point cloud transformers applied to collider physics
Mach. Learn.: Sci. Technol. 2, 035027 (2021) [Crossref]
Huerta et al., FAIR for AI: An interdisciplinary and international community building perspective
Sci Data 10, 487 (2023) [Crossref]
Biscarat et al., Event Classification with Multi-step Machine Learning
EPJ Web Conf. 251, 03036 (2021) [Crossref]
Kasieczka et al., Towards machine learning analytics for jet substructure
J. High Energ. Phys. 2020, 195 (2020) [Crossref]
Chen et al., A FAIR and AI-ready Higgs boson decay dataset
Sci Data 9, 31 (2022) [Crossref]
Dillon et al., Symmetries, safety, and self-supervision
SciPost Phys. 12, 188 (2022) [Crossref]
Bieringer et al., Measuring QCD Splittings with Invertible Networks
SciPost Phys. 10, 126 (2021) [Crossref]
Li et al., Reconstructing boosted Higgs jets from event image segmentation
J. High Energ. Phys. 2021, 156 (2021) [Crossref]
Barbosa et al., Probing a $$\textrm{Z}^{\prime }$$ with non-universal fermion couplings through top quark fusion, decays to bottom quarks, and machine learning techniques
Eur. Phys. J. C 83, 413 (2023) [Crossref]
Leigh et al., PC-JeDi: Diffusion for particle cloud generation in high energy physics
SciPost Phys. 16, 018 (2024) [Crossref]
Blance et al., Quantum machine learning for particle physics using a variational quantum classifier
J. High Energ. Phys. 2021, 212 (2021) [Crossref]
Kasieczka et al., The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics
Rep. Prog. Phys. 84, 124201 (2021) [Crossref]
Ju et al., Supervised jet clustering with graph neural networks for Lorentz boosted bosons
Phys. Rev. D 102, 075014 (2020) [Crossref]
Dillon et al., Better latent spaces for better autoencoders
SciPost Phys. 11, 061 (2021) [Crossref]
Moreno et al., Interaction networks for the identification of boosted H→bb¯ decays
Phys. Rev. D 102, 012010 (2020) [Crossref]
Kasieczka et al., Robust Jet Classifiers through Distance Correlation
Phys. Rev. Lett. 125, 122001 (2020) [Crossref]
Buhmann et al., Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
Comput Softw Big Sci 5, 13 (2021) [Crossref]
Tumasyan et al., Search for Higgs Boson Decay to a Charm Quark-Antiquark Pair in Proton-Proton Collisions at s=13 TeV
Phys. Rev. Lett. 131, 061801 (2023) [Crossref]
Khosa et al., Higgs boson tagging with the Lund jet plane
Phys. Rev. D 104, 055043 (2021) [Crossref]
Bose et al., Interplay of traditional methods and machine learning algorithms for tagging boosted objects
Eur. Phys. J. Spec. Top., (2024) [Crossref]
Dersy et al., Reconstructing S-matrix Phases with Machine Learning
J. High Energ. Phys. 2024, 200 (2024) [Crossref]
Heneka et al.,
472, 251 (2024) [Crossref]
Oleksiyuk et al., Cluster Scanning: a novel approach to resonance searches
J. High Energ. Phys. 2024, 163 (2024) [Crossref]
Chen et al., Boosted W and Z tagging with jet charge and deep learning
Phys. Rev. D 101, 053001 (2020) [Crossref]
Jang et al., Learning to increase matching efficiency in identifying additional b-jets in the $$\text {t}\bar{\text {t}}\text {b}\bar{\text {b}}$$ process
Eur. Phys. J. Plus 137, 870 (2022) [Crossref]
Araz et al., Quantum-probabilistic Hamiltonian learning for generative modeling and anomaly detection
Phys. Rev. A 108, 062422 (2023) [Crossref]
Chatterjee et al., Rotation-equivariant graph neural network for learning hadronic SMEFT effects
Phys. Rev. D 109, 076012 (2024) [Crossref]
Khosa et al., Using machine learning to disentangle LHC signatures of Dark Matter candidates
SciPost Phys. 10, 151 (2021) [Crossref]
Banelli et al., The present and future of four top operators
J. High Energ. Phys. 2021, 43 (2021) [Crossref]
Lasocha et al., Machine learning classification: Case of Higgs boson CP state in H→ττ decay at the LHC
Phys. Rev. D 100, 113001 (2019) [Crossref]
Chatham Strong, On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case
Mach. Learn.: Sci. Technol. 1, 045006 (2020) [Crossref]
Budhraja et al., Identifying heavy particle jets with a new nonlinear jet observable
Phys. Rev. D 102, 114036 (2020) [Crossref]
Aguilar-Saavedra, Pulling the Higgs and top needles from the jet stack with feature extended supervised tagging
Eur. Phys. J. C 81, 734 (2021) [Crossref]
Ghosh et al., A cautionary tale of decorrelating theory uncertainties
Eur. Phys. J. C 82, 46 (2022) [Crossref]
Kieseler, Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph, and image data
Eur. Phys. J. C 80, 886 (2020) [Crossref]
Lv et al., Deep learning jet images as a probe of light Higgsino dark matter at the LHC
Phys. Rev. D 106, 055008 (2022) [Crossref]
Kansal et al., JetNet: A Python package for accessing open datasets and benchmarking machine learning methods in high energy physics
JOSS 8, 5789 (2023) [Crossref]
Larkoski, QCD masterclass lectures on jet physics and machine learning
Eur. Phys. J. C 84, 1117 (2024) [Crossref]
Finke et al., Tree-based algorithms for weakly supervised anomaly detection
Phys. Rev. D 109, 034033 (2024) [Crossref]
Li et al., Tag Z boson jets via convolutional neural networks
Acta Phys. Sin. 70, 061301 (2021) [Crossref]
Algren et al., Decorrelation using optimal transport
Eur. Phys. J. C 84, 579 (2024) [Crossref]
Caletti et al., Jet angularities in Z+jet production at the LHC
J. High Energ. Phys. 2021, 76 (2021) [Crossref]
Bhimji et al., Snowmass 2021 Computational Frontier CompF4 Topical Group Report Storage and Processing Resource Access
Comput Softw Big Sci 7, 5 (2023) [Crossref]
Aad et al., Measurement of jet substructure in boosted tt¯ events with the ATLAS detector using 140 fb−1 of 13 TeV pp collisions
Phys. Rev. D 109, 112016 (2024) [Crossref]
Bhattacharya et al., Boosted top quark tagging and polarization measurement using machine learning
Phys. Rev. D 105, 042005 (2022) [Crossref]
Das et al., Feature selection with distance correlation
Phys. Rev. D 109, 054009 (2024) [Crossref]
Khot et al., A detailed study of interpretability of deep neural network based top taggers
Mach. Learn.: Sci. Technol. 4, 035003 (2023) [Crossref]
Omana Kuttan et al., A fast centrality-meter for heavy-ion collisions at the CBM experiment
Physics Letters B 811, 135872 135872 (2020) [Crossref]
Englert et al., Sensing Higgs boson cascade decays through memory
Phys. Rev. D 102, 095027 (2020) [Crossref]
Tumasyan et al., Search for Nonresonant Pair Production of Highly Energetic Higgs Bosons Decaying to Bottom Quarks
Phys. Rev. Lett. 131, 041803 (2023) [Crossref]
Mikuni et al., High-dimensional and permutation invariant anomaly detection
SciPost Phys. 16, 062 (2024) [Crossref]
Spelda et al., Learnability of state spaces of physical systems is undecidable
Journal of Computational Science 83, 102452 102452 (2024) [Crossref]
Bhardwaj et al., Equivariant, safe and sensitive — graph networks for new physics
J. High Energ. Phys. 2024, 245 (2024) [Crossref]
Andreassen et al., binary junipr: An Interpretable Probabilistic Model for Discrimination
Phys. Rev. Lett. 123, 182001 (2019) [Crossref]
Heinrich, Collider physics at the precision frontier
Physics Reports 922, 1 (2021) [Crossref]
Yu et al., Azimuthal Angular Correlation as a Boosted Top Jet Substructure
Phys. Rev. Lett. 129, 112001 (2022) [Crossref]
Dorigo et al., Toward the end-to-end optimization of particle physics instruments with differentiable programming
Reviews in Physics 10, 100085 100085 (2023) [Crossref]
Belyaev et al., Vectorlike top quark production via an electroweak dipole moment at a muon collider
Phys. Rev. D 108, 035016 (2023) [Crossref]
Lim et al., Morphology for jet classification
Phys. Rev. D 105, 014004 (2022) [Crossref]
Krupa et al., GPU coprocessors as a service for deep learning inference in high energy physics
Mach. Learn.: Sci. Technol. 2, 035005 (2021) [Crossref]
Ahmed et al., Application of deep learning in top pair and single top quark production at the LHC
Eur. Phys. J. Plus 138, 795 (2023) [Crossref]
Diefenbacher et al., CapsNets continuing the convolutional quest
SciPost Phys. 8, 023 (2020) [Crossref]
Anschuetz et al., Degeneracy engineering for classical and quantum annealing: A case study of sparse linear regression in collider physics
Phys. Rev. D 106, 056008 (2022) [Crossref]
Rankin et al.,
, 38 (2020) [Crossref]
Benato et al., Shared Data and Algorithms for Deep Learning in Fundamental Physics
Comput Softw Big Sci 6, 9 (2022) [Crossref]
Barman et al., Top-philic machine learning
Eur. Phys. J. Spec. Top., (2024) [Crossref]

Authors / Affiliations: mappings to Contributors and Organizations

See all Organizations.

¹ Gregor Kasieczka,
² Tilman Plehn,
² Anja Butter,
³ Kyle Cranmer,
⁴ Dipsikha Debnath,
⁵ Barry M. Dillon,
⁶ Malcolm Fairbairn,
⁵ Darius A. Faroughy,
⁷ Wojtek Fedorko,
⁷ Christophe Gay,
⁸ Loukas Gouskos,
⁵ ⁹ Jernej F. Kamenik,
¹⁰ Patrick Komiske,
¹ Simon Leiss,
⁷ Alison Lister,
³ ⁴ Sebastian Macaluso,
¹⁰ Eric Metodiev,
¹¹ Liam Moore,
¹² ¹³ Benjamin Nachman,
¹⁴ ¹⁵ Karl Nordström,
⁷ Jannicke Pearkes,
⁸ Huilin Qu,
¹⁶ Yannik Rath,
¹⁶ Marcel Rieger,
⁴ David Shih,
² Jennifer Thompson,
⁶ Sreedevi Varma

Funders for the research work leading to this publication

National Science Foundation [NSF]
Nvidia (through Organization: Nvidia (United States))
United States Department of Energy [DOE]