skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Anomaly Detection for Resonant New Physics with Machine Learning

Abstract

Despite extensive theoretical motivation for physics beyond the Standard Model (BSM) of particle physics, searches at the Large Hadron Collider (LHC) have found no significant evidence for BSM physics. Therefore, it is essential to broaden the sensitivity of the search program to include unexpected scenarios. We present a new model-agnostic anomaly detection technique that naturally benefits from modern machine learning algorithms. The only requirement on the signal for this new procedure is that it is localized in at least one known direction in phase space. Any other directions of phase space that are uncorrelated with the localized one can be used to search for unexpected features. This new method is applied to the dijet resonance search to show that it can turn a modest 2σ excess into a 7σ excess for a model with an intermediate BSM particle that is not currently targeted by a dedicated search.

Authors:
 [1]; ORCiD logo [2];  [3]
  1. Univ. of Maryland, College Park, MD (United States); Johns Hopkins Univ., Baltimore, MD (United States)
  2. Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
  3. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Berkeley, CA (United States)
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25)
OSTI Identifier:
1485531
Alternate Identifier(s):
OSTI ID: 1462217; OSTI ID: 1494114
Report Number(s):
arXiv:1805.02664; FERMILAB-PUB-18-180-T
Journal ID: ISSN 0031-9007; PRLTAO; 1672143; TRN: US1902122
Grant/Contract Number:  
AC02-07CH11359; AC02-05CH11231
Resource Type:
Published Article
Journal Name:
Physical Review Letters
Additional Journal Information:
Journal Volume: 121; Journal Issue: 24; Journal ID: ISSN 0031-9007
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats

Collins, Jack H., Howe, Kiel, and Nachman, Benjamin. Anomaly Detection for Resonant New Physics with Machine Learning. United States: N. p., 2018. Web. doi:10.1103/PhysRevLett.121.241803.
Collins, Jack H., Howe, Kiel, & Nachman, Benjamin. Anomaly Detection for Resonant New Physics with Machine Learning. United States. doi:10.1103/PhysRevLett.121.241803.
Collins, Jack H., Howe, Kiel, and Nachman, Benjamin. Wed . "Anomaly Detection for Resonant New Physics with Machine Learning". United States. doi:10.1103/PhysRevLett.121.241803.
@article{osti_1485531,
title = {Anomaly Detection for Resonant New Physics with Machine Learning},
author = {Collins, Jack H. and Howe, Kiel and Nachman, Benjamin},
abstractNote = {Despite extensive theoretical motivation for physics beyond the Standard Model (BSM) of particle physics, searches at the Large Hadron Collider (LHC) have found no significant evidence for BSM physics. Therefore, it is essential to broaden the sensitivity of the search program to include unexpected scenarios. We present a new model-agnostic anomaly detection technique that naturally benefits from modern machine learning algorithms. The only requirement on the signal for this new procedure is that it is localized in at least one known direction in phase space. Any other directions of phase space that are uncorrelated with the localized one can be used to search for unexpected features. This new method is applied to the dijet resonance search to show that it can turn a modest 2σ excess into a 7σ excess for a model with an intermediate BSM particle that is not currently targeted by a dedicated search.},
doi = {10.1103/PhysRevLett.121.241803},
journal = {Physical Review Letters},
number = 24,
volume = 121,
place = {United States},
year = {2018},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
DOI: 10.1103/PhysRevLett.121.241803

Citation Metrics:
Cited by: 14 works
Citation information provided by
Web of Science

Figures / Tables:

FIG. 1. FIG. 1.: Left: mJJ distribution of dijet events (including injected signal, indicated by the filled histogram) before and after applying jet substructure cuts using the NN classifier output for the mJJ ≃ 3 TeV mass hypothesis. The dashed red lines indicate the fit to the data points outside of themore » signal region, with the gray bands representing the fit uncertainties. The top set of markers represent the raw dijet distribution with no cut applied, while the subsequent sets of markers have cuts applied at thresholds with efficiency of 10−1, 10−2, 2 × 10−3, and 2 × 10−4. Right: Local p0-values for a range of signal mass hypotheses in the case that no signal has been injected (left), and in the case that a 3 TeV resonance signal has been injected (right). The dashed lines correspond to the case where no substructure cut is applied, and the various solid lines correspond to cuts on the classifier output with efficiencies of 10−1, 10−2, and 2 × 10−3.« less

Save / Share:

Works referenced in this record:

A general search for new phenomena in ep scattering at HERA
journal, November 2004


uBoost: a boosting method for producing uniform selection efficiencies from multivariate classifiers
journal, December 2013


Jet Substructure as a New Higgs-Search Channel at the Large Hadron Collider
journal, June 2008


Quasi-model-independent search for new physics at large transverse momentum
journal, June 2001


On the Problem of the Most Efficient Tests of Statistical Hypotheses
journal, January 1933

  • Neyman, J.; Pearson, E. S.
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 231, Issue 694-706
  • DOI: 10.1098/rsta.1933.0009

Model-independent and quasi-model-independent search for new physics at CDF
journal, July 2008


: A statistical tool to unfold data distributions
journal, December 2005

  • Pivk, M.; Le Diberder, F. R.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 555, Issue 1-2
  • DOI: 10.1016/j.nima.2005.08.106

Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
journal, May 2016

  • Dolen, James; Harris, Philip; Marzani, Simone
  • Journal of High Energy Physics, Vol. 2016, Issue 5
  • DOI: 10.1007/JHEP05(2016)156

Decorrelated jet substructure tagging using adversarial neural networks
journal, October 2017


A brief introduction to PYTHIA 8.1
journal, June 2008

  • Sjöstrand, Torbjörn; Mrenna, Stephen; Skands, Peter
  • Computer Physics Communications, Vol. 178, Issue 11
  • DOI: 10.1016/j.cpc.2008.01.036

Search for Low Mass Vector Resonances Decaying to Quark-Antiquark Pairs in Proton-Proton Collisions at s = 13 TeV
journal, September 2017


Classification without labels: learning from mixed samples in high energy physics
journal, October 2017

  • Metodiev, Eric M.; Nachman, Benjamin; Thaler, Jesse
  • Journal of High Energy Physics, Vol. 2017, Issue 10
  • DOI: 10.1007/JHEP10(2017)174

Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
journal, September 2012


DELPHES 3: a modular framework for fast simulation of a generic collider experiment
journal, February 2014

  • de Favereau, J.; Delaere, C.; Demin, P.
  • Journal of High Energy Physics, Vol. 2014, Issue 2
  • DOI: 10.1007/JHEP02(2014)057

Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
journal, September 2012


The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
journal, July 2014

  • Alwall, J.; Frederix, R.; Frixione, S.
  • Journal of High Energy Physics, Vol. 2014, Issue 7
  • DOI: 10.1007/JHEP07(2014)079

WW scattering at the CERN LHC
journal, May 2002


Flavor universal resonances and warped gravity
journal, January 2017

  • Agashe, Kaustubh; Du, Peizhi; Hong, Sungwoo
  • Journal of High Energy Physics, Vol. 2017, Issue 1
  • DOI: 10.1007/JHEP01(2017)016

A generic anti-QCD jet tagger
journal, November 2017

  • Aguilar-Saavedra, J. A.; Collins, Jack; Mishra, Rashmish K.
  • Journal of High Energy Physics, Vol. 2017, Issue 11
  • DOI: 10.1007/JHEP11(2017)163

A general search for new phenomena at HERA
journal, April 2009


Searches for new particles using cone and cluster jet algorithms: a comparative study
journal, March 1994

  • Seymour, Michael H.
  • Zeitschrift für Physik C Particles and Fields, Vol. 62, Issue 1
  • DOI: 10.1007/BF01559532

Detecting a boosted diboson resonance
journal, November 2018

  • Agashe, Kaustubh; Collins, Jack H.; Du, Peizhi
  • Journal of High Energy Physics, Vol. 2018, Issue 11
  • DOI: 10.1007/JHEP11(2018)027

Global search for new physics with 2.0 fb 1 at CDF
journal, January 2009


Identifying boosted objects with N-subjettiness
journal, March 2011


Systematic analysis of HEP collider data
journal, November 2004

  • Knuteson, Bruce
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 534, Issue 1-2
  • DOI: 10.1016/j.nima.2004.07.050

Convolved substructure: analytically decorrelating jet substructure observables
journal, May 2018

  • Moult, Ian; Nachman, Benjamin; Neill, Duff
  • Journal of High Energy Physics, Vol. 2018, Issue 5
  • DOI: 10.1007/JHEP05(2018)002

Erratum to: Asymptotic formulae for likelihood-based tests of new physics
journal, July 2013


Asymptotic formulae for likelihood-based tests of new physics
journal, February 2011


Search for new physics in e μ X data at DØ using SLEUTH: A quasi-model-independent search strategy for new physics
journal, October 2000


Beyond the standard model with the LHC
journal, July 2007


    Figures / Tables found in this record:

      Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.