Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Benchmark data and model independent event classification for the large hadron collider

Aarrestad, Thea ; van Beekveld, Melissa ; Bona, Marcella ; Boveia, Antonio ; Caron, Sascha ; Davies, Joe ; De Simone, Andrea ; Doglioni, Caterina LU ; Duarte, Javier M. and Farbin, Amir , et al. (2022) In SciPost Physics 12(1).
Abstract

We describe the outcome of a data challenge conducted as part of the Dark Machines (https://www.darkmachines.org) initiative and the Les Houches 2019 workshop on Physics at TeV colliders. The challenged aims to detect signals of new physics at the Large Hadron Collider (LHC) using unsupervised machine learning algorithms. First, we propose how an anomaly score could be implemented to define model-independent signal regions in LHC searches. We define and describe a large benchmark dataset, consisting of > 1 billion simulated LHC events corresponding to 10 fb−1 of proton-proton collisions at a center-of-mass energy of 13 TeV. We then review a wide range of anomaly detection and density estimation algorithms, developed in the... (More)

We describe the outcome of a data challenge conducted as part of the Dark Machines (https://www.darkmachines.org) initiative and the Les Houches 2019 workshop on Physics at TeV colliders. The challenged aims to detect signals of new physics at the Large Hadron Collider (LHC) using unsupervised machine learning algorithms. First, we propose how an anomaly score could be implemented to define model-independent signal regions in LHC searches. We define and describe a large benchmark dataset, consisting of > 1 billion simulated LHC events corresponding to 10 fb−1 of proton-proton collisions at a center-of-mass energy of 13 TeV. We then review a wide range of anomaly detection and density estimation algorithms, developed in the context of the data challenge, and we measure their performance in a set of realistic analysis environments. We draw a number of useful conclusions that will aid the development of unsupervised new physics searches during the third run of the LHC, and provide our benchmark dataset for future studies at https://www.phenoMLdata.org. Code to reproduce the analysis is provided at https://github.com/bostdiek/DarkMachines-UnsupervisedChallenge.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
SciPost Physics
volume
12
issue
1
article number
043
publisher
SciPost
external identifiers
  • scopus:85124788724
ISSN
2542-4653
DOI
10.21468/SCIPOSTPHYS.12.1.043
language
English
LU publication?
yes
id
27248735-9983-4f09-bd60-5e9532b68388
date added to LUP
2022-05-19 14:24:07
date last changed
2023-04-05 16:27:36
@article{27248735-9983-4f09-bd60-5e9532b68388,
  abstract     = {{<p>We describe the outcome of a data challenge conducted as part of the Dark Machines (https://www.darkmachines.org) initiative and the Les Houches 2019 workshop on Physics at TeV colliders. The challenged aims to detect signals of new physics at the Large Hadron Collider (LHC) using unsupervised machine learning algorithms. First, we propose how an anomaly score could be implemented to define model-independent signal regions in LHC searches. We define and describe a large benchmark dataset, consisting of &gt; 1 billion simulated LHC events corresponding to 10 fb<sup>−1</sup> of proton-proton collisions at a center-of-mass energy of 13 TeV. We then review a wide range of anomaly detection and density estimation algorithms, developed in the context of the data challenge, and we measure their performance in a set of realistic analysis environments. We draw a number of useful conclusions that will aid the development of unsupervised new physics searches during the third run of the LHC, and provide our benchmark dataset for future studies at https://www.phenoMLdata.org. Code to reproduce the analysis is provided at https://github.com/bostdiek/DarkMachines-UnsupervisedChallenge.</p>}},
  author       = {{Aarrestad, Thea and van Beekveld, Melissa and Bona, Marcella and Boveia, Antonio and Caron, Sascha and Davies, Joe and De Simone, Andrea and Doglioni, Caterina and Duarte, Javier M. and Farbin, Amir and Gupta, Honey and Hendriks, Luc and Heinrich, Lukas and Howarth, James and Jawahar, Pratik and Jueid, Adil and Lastow, Jessica and Leinweber, Adam and Mamuzic, Judita and Merényi, Erzsébet and Morandini, Alessandro and Moskvitina, Polina and Nellist, Clara and Ngadiuba, Jennifer and Ostdiek, Bryan and Pierini, Maurizio and Ravina, Baptiste and de Austri, Roberto R. and Sekmen, Sezen and Touranakou, Mary and Vaškevičiūte, Marija and Vilalta, Ricardo and Vlimant, Jean Roch and Verheyen, Rob and White, Martin and Wulff, Eric and Wallin, Erik and Wozniak, Kinga A. and Zhang, Zhongyi}},
  issn         = {{2542-4653}},
  language     = {{eng}},
  month        = {{01}},
  number       = {{1}},
  publisher    = {{SciPost}},
  series       = {{SciPost Physics}},
  title        = {{Benchmark data and model independent event classification for the large hadron collider}},
  url          = {{http://dx.doi.org/10.21468/SCIPOSTPHYS.12.1.043}},
  doi          = {{10.21468/SCIPOSTPHYS.12.1.043}},
  volume       = {{12}},
  year         = {{2022}},
}