- Physical Review Journals
All JournalsPhysics Magazine

Physical Review D

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Letter
  • Open Access

Data-driven and model-agnostic approach to solving combinatorial assignment problems in searches for new physics

Anthony Badea1,2,* and Javier Montejo Berlingen3,4,†

  • 1Harvard University, Cambridge, Massachusetts 02138, USA
  • 2University of Chicago, Chicago, Illinois 60637, USA
  • 3Instituto de Física de Altas Energías, Campus UAB, 08193 Bellaterra (Barcelona), Spain
  • 4QUP, KEK, 1-1 Ōho, Tsukuba, Ibaraki 300-3256, Japan

  • *anthony.badea@cern.ch
  • †jmontejo@cern.ch
PDF

Phys. Rev. D 109, L011702 – Published 9 January, 2024

DOI: https://doi.org/10.1103/PhysRevD.109.L011702

Abstract

We present a novel approach to solving combinatorial assignment problems in particle physics. The correct assignment of decay products to parent particles is achieved in a model-agnostic fashion by introducing a neural network architecture, passwd-abc, which combines a custom layer based on attention mechanisms and dual autoencoders. We demonstrate how the network, trained purely on background events in an unsupervised setting, is capable of reconstructing correctly hypothetical new particles regardless of their mass, decay multiplicity, and substructure, and produces simultaneously an anomaly score that can be used to efficiently suppress the background. This model allows the extension of the suite of searches for localized excesses to include nonresonant particle pair production where the reconstruction of the two resonant masses is thwarted by combinatorics.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (42)

  1. ATLAS Collaboration, Phys. Lett. B 842, 137963 (2023).
  2. M. Aaboud et al. (ATLAS Collaboration), Phys. Rev. D 98, 052008 (2018).
  3. M. Aaboud et al. (ATLAS Collaboration), J. High Energy Phys. 05 (2019) 142.
  4. A. M. Sirunyan et al. (CMS Collaboration), Phys. Lett. B 798, 134952 (2019).
  5. A. Tumasyan et al. (CMS Collaboration), Eur. Phys. J. C 81, 970 (2021).
  6. ATLAS, Supersymmetry summary plots, Report No. ATL-PHYS-PUB-2023-025, https://cds.cern.ch/record/2852738.
  7. CMS, CMS Exotica summary plots, https://twiki.cern.ch/twiki/bin/view/CMSPublic/SummaryPlotsEXO13TeV.
  8. J. J. Aubert et al. (E598 Collaboration), Phys. Rev. Lett. 33, 1404 (1974).
  9. J. E. Augustin et al. (SLAC-SP-017 Collaboration), Phys. Rev. Lett. 33, 1406 (1974).
  10. G. Aad et al. (ATLAS Collaboration), Phys. Lett. B 716, 1 (2012).
  11. S. Chatrchyan et al. (CMS Collaboration), Phys. Lett. B 716, 30 (2012).
  12. M. Aaboud et al. (ATLAS Collaboration), Eur. Phys. J. C 78, 250 (2018).
  13. M. Aaboud et al. (ATLAS Collaboration), Phys. Rev. D 98, 092002 (2018).
  14. ATLAS Collaboration, Phys. Rev. D 108, 052003 (2023).
  15. G. Aad et al. (ATLAS Collaboration), Phys. Rev. D 108, 112005 (2023).
  16. M. J. Fenton, A. Shmakov, T.-W. Ho, S.-C. Hsu, D. Whiteson, and P. Baldi, Phys. Rev. D 105, 112008 (2022).
  17. S. Qiu, S. Han, X. Ju, B. Nachman, and H. Wang, Phys. Rev. D 107, 114029 (2023).
  18. A. Badea, W. J. Fawcett, J. Huth, T. J. Khoo, R. Poggi, and L. Lee, Phys. Rev. D 106, 016001 (2022).
  19. L. Ehrke, J. A. Raine, K. Zoch, M. Guth, and T. Golling, Phys. Rev. D 107, 116019 (2023).
  20. A. Shmakov, M. J. Fenton, T.-W. Ho, S.-C. Hsu, D. Whiteson, and P. Baldi, SciPost Phys. 12, 178 (2022).
  21. J. S. H. Lee, I. Park, I. J. Watson, and S. Yang, arXiv:2012.03542.
  22. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, arXiv:1706.03762.
  23. C. J. Maddison, A. Mnih, and Y. W. Teh, arXiv:1611.00712.
  24. E. Jang, S. Gu, and B. Poole, arXiv:1611.01144.
  25. P. T. Komiske, E. M. Metodiev, and J. Thaler, Phys. Rev. Lett. 123, 041801 (2019).
  26. P. T. Komiske, E. M. Metodiev, and J. Thaler, J. High Energy Phys. 07 (2020) 006.
  27. F. Schroff, D. Kalenichenko, and J. Philbin, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Boston, MA, USA, 2015), https://ieeexplore.ieee.org/document/7298682.
  28. T. Hua, W. Wang, Z. Xue, S. Ren, Y. Wang, and H. Zhao, arXiv:2105.00470.
  29. L. Jing, P. Vincent, Y. LeCun, and Y. Tian, arXiv:2110.09348.
  30. R. Barbier et al., Phys. Rep. 420, 1 (2005).
  31. R. N. Mohapatra, Phys. Scr. 90, 088004 (2015).
  32. C. Csáki, Y. Grossman, and B. Heidenreich, Phys. Rev. D 85, 095009 (2012).
  33. J. Alwall, R. Frederix, S. Frixione, V. Hirschi, F. Maltoni, O. Mattelaer, H. S. Shao, T. Stelzer, P. Torrielli, and M. Zaro, J. High Energy Phys. 07 (2014) 079.
  34. B. Fuks, Int. J. Mod. Phys. A 27, 1230007 (2012).
  35. T. Sjöstrand, S. Ask, J. R. Christiansen, R. Corke, N. Desai, P. Ilten, S. Mrenna, S. Prestel, C. O. Rasmussen, and P. Z. Skands, Comput. Phys. Commun. 191, 159 (2015).
  36. D. P. Kingma and J. Ba, arXiv:1412.6980.
  37. G. Louppe, M. Kagan, and K. Cranmer, arXiv:1611.01046.
  38. C. Shimmin, P. Sadowski, P. Baldi, E. Weik, D. Whiteson, E. Goul, and A. Søgaard, Phys. Rev. D 96, 074034 (2017).
  39. O. Kitouni, B. Nachman, C. Weisser, and M. Williams, J. High Energy Phys. 04 (2020) 070.
  40. G. Kasieczka and D. Shih, Phys. Rev. Lett. 125, 122001 (2020).
  41. S. Klein and T. Golling, arXiv:2211.02486.
  42. M. Algren, J. A. Raine, and T. Golling, arXiv:2307.05187.

Outline

Information

Phys. Rev. D 109, L011702– Published 9 January, 2024
  • Received 13 September 2023
  • Accepted 18 December 2023
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Funded by SCOAP3.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation