Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Search for New Phenomena in Two-Body Invariant Mass Distributions Using Unsupervised Machine Learning for Anomaly Detection at √s = 13 TeV with the ATLAS Detector

Aad, G. ; Åkesson, T.P.A. LU orcid ; Corrigan, E.E. LU ; Doglioni, C. LU ; Geisen, J. LU orcid ; Hansen, E. LU ; Hedberg, V. LU ; Herde, Hannah LU orcid ; Konya, B. LU and Lytken, E. LU orcid , et al. (2024) In Physical Review Letters 132(8).
Abstract
Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb−1 of pp collisions at √s ¼ 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b jet and either one lepton (e; μ), photon, or second light jet or b jet in the anomalous regions. No significant deviations from the background hypotheses are observed. Limits on contributions from generic Gaussian signals with various widths of the... (More)
Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb−1 of pp collisions at √s ¼ 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b jet and either one lepton (e; μ), photon, or second light jet or b jet in the anomalous regions. No significant deviations from the background hypotheses are observed. Limits on contributions from generic Gaussian signals with various widths of the resonance mass are obtained for nine invariant masses in the anomalous regions. © 2024 CERN, for the ATLAS Collaboration. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; and (Less)
author collaboration
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Anomaly detection, Machine learning, Tellurium compounds, Anomalous regions, ATLAS detectors, Auto encoders, Invariant mass distribution, Large Hadron Collider, Large-hadron colliders, Region-based, Unsupervised anomaly detection, Unsupervised machine learning, Mass spectrometry
in
Physical Review Letters
volume
132
issue
8
article number
081801
publisher
American Physical Society
external identifiers
  • scopus:85186742137
  • pmid:38457710
ISSN
0031-9007
DOI
10.1103/PhysRevLett.132.081801
language
English
LU publication?
yes
additional info
Number of authors = 2909 EID = 85186742137 Article no = 081801 Affiliation = Aad G., CPPM, Aix-Marseille Université, CNRS, IN2P3, Marseille, France Affiliation = Zou W., Nevis Laboratory, Columbia University, Irvington, NY, United States Affiliation = Zwalinski L., CERN, Geneva, Switzerland
id
f0f650f1-831f-4456-adac-b898d2580c3b
date added to LUP
2024-03-28 12:56:07
date last changed
2024-03-29 03:07:11
@article{f0f650f1-831f-4456-adac-b898d2580c3b,
  abstract     = {{Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb−1 of pp collisions at √s ¼ 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b jet and either one lepton (e; μ), photon, or second light jet or b jet in the anomalous regions. No significant deviations from the background hypotheses are observed. Limits on contributions from generic Gaussian signals with various widths of the resonance mass are obtained for nine invariant masses in the anomalous regions. © 2024 CERN, for the ATLAS Collaboration.}},
  author       = {{Aad, G. and Åkesson, T.P.A. and Corrigan, E.E. and Doglioni, C. and Geisen, J. and Hansen, E. and Hedberg, V. and Herde, Hannah and Konya, B. and Lytken, E. and Poettgen, R. and Simpson, N.D. and Smirnova, O. and Zwalinski, L.}},
  issn         = {{0031-9007}},
  keywords     = {{Anomaly detection; Machine learning; Tellurium compounds; Anomalous regions; ATLAS detectors; Auto encoders; Invariant mass distribution; Large Hadron Collider; Large-hadron colliders; Region-based; Unsupervised anomaly detection; Unsupervised machine learning; Mass spectrometry}},
  language     = {{eng}},
  number       = {{8}},
  publisher    = {{American Physical Society}},
  series       = {{Physical Review Letters}},
  title        = {{Search for New Phenomena in Two-Body Invariant Mass Distributions Using Unsupervised Machine Learning for Anomaly Detection at √s = 13 TeV with the ATLAS Detector}},
  url          = {{http://dx.doi.org/10.1103/PhysRevLett.132.081801}},
  doi          = {{10.1103/PhysRevLett.132.081801}},
  volume       = {{132}},
  year         = {{2024}},
}