The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics

Abstract
A new paradigm for data-driven, model-agnostic new physics searches at colliders is emerging, and aims to leverage recent breakthroughs in anomaly detection and machine learning. In order to develop and benchmark new anomaly detection methods within this framework, it is essential to have standard datasets. To this end, we have created the LHC Olympics 2020, a community challenge accompanied by a set of simulated collider events. Participants in these Olympics have developed their methods using an R&D dataset and then tested them on black boxes: datasets with an unknown anomaly (or not). Methods made use of modern machine learning tools and were based on unsupervised learning (autoencoders, generative adversarial networks, normalizing flows), weakly supervised learning, and semi-supervised learning. This paper will review the LHC Olympics 2020 challenge, including an overview of the competition, a description of methods deployed in the competition, lessons learned from the experience, and implications for data analyses with future datasets as well as future colliders.

Topics

No keywords indexed for this article. Browse by subject →

References

164

[1]

Aad "Observation of a new particle in the search for the standard model Higgs boson with the ATLAS detector at the LHC" Phys. Lett. B (2012) 10.1016/j.physletb.2012.08.020

[2]

Chatrchyan "Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC" Phys. Lett. B (2012) 10.1016/j.physletb.2012.08.021

[3]

ATLAS Collaboration "Exotic physics searches" (2019)

[4]

ATLAS Collaboration "Supersymmetry searches" (2019)

[5]

ATLAS Collaboration "Higgs and diboson searches" (2019)

[6]

CMS Collaboration "CMS exotica public physics results" (2019)

[7]

CMS Collaboration "CMS supersymmetry physics results" (2019)

[8]

CMS Collaboration "CMS beyond-two-generations (B2G) public physics results" (2019)

[9]

LHCb Collaboration "Publications of the QCD, electroweak and exotica working group" (2019)

[10]

Craig "The unexplored landscape of two-body resonances" Acta Phys. Pol. B (2019) 10.5506/aphyspolb.50.837

[11]

Kim "The motivation and status of two-body resonance decays after the LHC run 2 and beyond" J. High Energy Phys. (2020) 10.1007/jhep04(2020)030

[12]

Button "Pion–pion interaction in the reaction p¯+p→2π++2π−+nπ0" Phys. Rev. (1962) 10.1103/physrev.126.1858

[13]

Knuteson "A quasi-model-independent search for new high p T physics at D0" (2000)

[14]

Abbott "Search for new physics in eμX data at DØ using Sherlock: a quasi model independent search strategy for new physics" Phys. Rev. D (2000) 10.1103/physrevd.62.092004

[15]

Abazov "A quasi model independent search for new physics at large transverse momentum" Phys. Rev. D (2001) 10.1103/physrevd.64.012004

[16]

Abbott "A quasi-model-independent search for new high p T physics at DØ" Phys. Rev. Lett. (2001) 10.1103/physrevlett.86.3712

[17]

Aaron "A general search for new phenomena at HERA" Phys. Lett. B (2009) 10.1016/j.physletb.2009.03.034

[18]

Aktas "A General search for new phenomena in ep scattering at HERA" Phys. Lett. B (2004) 10.1016/s0370-2693(04)01396-6

[19]

Cranmer "Searching for new physics: contributions to LEP and the LHC" (2005)

[20]

Aaltonen "Model-independent and quasi-model-independent search for new physics at CDF" Phys. Rev. D (2008) 10.1103/physrevd.78.012002

[21]

Aaltonen "Model-independent global search for new high-p(T) physics at CDF" (2017)

[22]

Aaltonen "Global search for new physics with 2.0 fb−1 at CDF" Phys. Rev. D (2009) 10.1103/physrevd.79.011101

[23]

CMS Collaboration "MUSiC, a model unspecific search for new physics, in pp collisions at s=8 TeV" (2017)

[24]

CMS Collaboration "Model unspecific search for new physics in pp collisions at s= 7 TeV" (2011)

[25]

CMS Collaboration "MUSiC, a model unspecific search for new physics, in pp collisions at s=13 TeV" (2020)

[26]

Sirunyan "MUSiC: a model unspecific search for new physics in proton–proton collisions at s= 13 TeV" (2020)

[27]

Aaboud "A strategy for a general search for new phenomena using data-derived signal regions and its application within the ATLAS experiment" Eur. Phys. J. C (2019) 10.1140/epjc/s10052-019-6540-y

[28]

ATLAS Collaboration "A general search for new phenomena with the ATLAS detector in pp collisions at s=8 TeV" (2014)

[29]

ATLAS Collaboration "A general search for new phenomena with the ATLAS detector in pp collisions at s=7 TeV" (2012)

[30]

Gross "Trial factors for the look elsewhere effect in high energy physics" Eur. Phys. J. C (2010) 10.1140/epjc/s10052-010-1470-8

[31]

(2020)

[32]

(2005)

[33]

(2006)

[34]

(2006)

[35]

(2007)

[36]

(2020)

[37]

(2020)

[38]

Kasieczka G Nachman B Shih D 2019 Official Datasets for LHC Olympics 2020 Anomaly Detection Challenge https://doi.org/10.5281/zenodo.3596919 10.5281/zenodo.3596919

[39]

IPython: A System for Interactive Scientific Computing

Fernando Perez, Brian E. Granger

Computing in Science & Engineering 2007 10.1109/mcse.2007.53

[40]

Dawe N Rodrigues E Schreiner H Ostdiek B Kalinkin D Marcel R Meehan S 2020 scikit-hep/pyjet: Version 1.8.0 https://doi.org/10.5281/zenodo.4289190 10.5281/zenodo.4289190

[41]

Cacciari "FastJet user manual" Eur. Phys. J. C (2012) 10.1140/epjc/s10052-012-1896-2

[42]

Cacciari "Dispelling the N3 myth for the kt jet-finder" Phys. Lett. B (2006) 10.1016/j.physletb.2006.08.037

[43]

Sjöstrand "PYTHIA 6.4 physics and manual" J. High Energy Phys. (2006) 10.1088/1126-6708/2006/05/026

[44]

Sjöstrand "An introduction to PYTHIA 8.2" Comput. Phys. Commun. (2015) 10.1016/j.cpc.2015.01.024

[45]

de Favereau "DELPHES 3, a modular framework for fast simulation of a generic collider experiment" J. High Energy Phys. (2014) 10.1007/jhep02(2014)057

[46]

Mertens "New features in Delphes 3" J. Phys.: Conf. Ser. (2015) 10.1088/1742-6596/608/1/012045

[47]

Selvaggi "DELPHES 3: a modular framework for fast-simulation of generic collider experiments" J. Phys.: Conf. Ser. (2014) 10.1088/1742-6596/523/1/012033

[48]

Cacciari "The anti-ktjet clustering algorithm" J. High Energy Phys. (2008) 10.1088/1126-6708/2008/04/063

[49]

McKinney "Data structures for statistical computing in python" (2010)

[50]

Koranne "Hierarchical data format 5: HDF5" (2011)

Showing 50 of 164 references

Cited By

128

Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays

S. T. Roche, Q. Bayer · 2024

Nature Communications

Scientific discovery in the age of artificial intelligence

Hanchen Wang, Tianfan Fu · 2023

Nature

Deep Set Auto Encoders for Anomaly Detection in Particle Physics

Bryan Ostdiek · 2022

SciPost Physics

Autoencoders on field-programmable gate arrays for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider

Ekaterina Govorkova, Ema Puljak · 2022

Nature Machine Intelligence

Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

Pratik Jawahar, Thea Aarrestad · 2022

Frontiers in Big Data

The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider

Thea Aarrestad, Melissa van Beekveld · 2022

SciPost Physics

Leveraging universality of jet taggers through transfer learning

Frédéric A. Dreyer, Radosław Grabarczyk · 2022

The European Physical Journal C

Mining for Gluon Saturation at Colliders

Astrid Morreale, Farid Salazar · 2021

Universe

Metrics

128

Citations

164

References

Details

Published: Dec 01, 2021
Vol/Issue: 84(12)
Pages: 124201
License: View

Authors

Lawrence Berkeley National Laboratory

Horia Hulubei National Institute of Physics and Nuclear Engineering

CNRS/IN2P3

Laboratório de Instrumentação e Física Experimental de Partículas-LIP

University of Pennsylvania

Silviu-Marian Udrescu

Funding

Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung Award: 200020-182037

National Science Foundation Award: 190444

Deutsche Forschungsgemeinschaft Award: 390833306

‘la Caixa’ Foundation Award: 100010434

U.S. Department of Energy Award: DE-AC02-05CH11231

Cite This Article

G. Kasieczka, B. P. Nachman, David Shih, et al. (2021). The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics. Reports on Progress in Physics, 84(12), 124201. https://doi.org/10.1088/1361-6633/ac36b9

The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics

You May Also Like