- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Letters

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
  • Open Access

Incorporating Physical Priors into Weakly Supervised Anomaly Detection

Chi Lung Cheng1,2,*, Gup Singh2,†, and Benjamin Nachman2,3,4,5,‡

  • *Contact author: ccheng84@wisc.edu
  • †Contact author: gupsingh@berkeley.edu
  • ‡Contact author: bpnachman@lbl.gov
PDF

Phys. Rev. Lett. 135, 021801 – Published 7 July, 2025

DOI: https://doi.org/10.1103/8259-wt5p

Abstract

We propose a new machine-learning-based anomaly detection strategy for comparing data with a background-only reference (a form of weak supervision). The sensitivity of previous strategies degrades significantly when the signal is too rare or there are many unhelpful features. Our prior-assisted weak supervision (PAWS) method incorporates information from a class of signal models to significantly enhance the search sensitivity of weakly supervised approaches. As long as the true signal is in the prespecified class, PAWS matches the sensitivity of a dedicated, fully supervised method without specifying the exact parameters ahead of time. On the benchmark LHC Olympics anomaly detection dataset, our mix of semisupervised and weakly supervised learning is able to extend the sensitivity over previous methods by a factor of 10 in cross section. Furthermore, if we add irrelevant (noise) dimensions to the inputs, classical methods degrade by another factor of 10 in cross section while PAWS remains insensitive to noise. This new approach could be applied in a number of scenarios and pushes the frontier of sensitivity between completely model-agnostic approaches and fully model-specific searches.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (52)

  1. G. Kasieczka et al., The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics, Rep. Prog. Phys. 84, 124201 (2021).
  2. T. Aarrestad et al., The dark machines anomaly score challenge: Benchmark data and model independent event classification for the large hadron collider, SciPost Phys. 12, 043 (2022).
  3. G. Karagiorgi, G. Kasieczka, S. Kravitz, B. Nachman, and D. Shih, Machine learning in the search for new fundamental physics, Nat. Rev. Phys. 4, 399 (2022).
  4. Aad, Georges et al. (ATLAS Collaboration), Dijet resonance search with weak supervision using s=13  TeV pp collisions in the ATLAS detector, Phys. Rev. Lett. 125, 131801 (2020).
  5. Aad, Georges et al. (ATLAS Collaboration), 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, Phys. Rev. Lett. 132, 081801 (2024).
  6. Aad, Georges et al. (ATLAS Collaboration), Anomaly detection search for new resonances decaying into a Higgs boson and a generic new particle X in hadronic final states using s=13  TeV pp collisions with the ATLAS detector, Phys. Rev. D 108, 052009 (2023).
  7. Chekhovsky, Vladimir et al. (CMS Collaboration), Model-agnostic search for dijet resonances with anomalous jet substructure in proton-proton collisions at s=13  TeV, Technical Report, CERN, Geneva, 2024.
  8. D. Shih, M. R. Buckley, L. Necib, and J. Tamanas, via machinae: Searching for stellar streams using unsupervised machine learning, Mon. Not. R. Astron. Soc. 509, 5992 (2021).
  9. D. Shih, M. R. Buckley, and L. Necib, Via Machinae 2.0: Full-sky, model-agnostic search for stellar streams in Gaia DR2, Mon. Not. R. Astron. Soc. 529, 4745 (2024).
  10. M. Pettee, S. Thanvantri, B. Nachman, D. Shih, M. R. Buckley, and J. H. Collins, Weakly-supervised anomaly detection in the milky way, Mon. Not. R. Astron. Soc. 527, 8459 (2023).
  11. D. Sengupta, S. Mulligan, D. Shih, J. A. Raine, and T. Golling, SkyCURTAINs: Model agnostic search for Stellar Streams with Gaia data, Mon. Not. R. Astron. Soc. 536, 1104 (2024).
  12. J. H. Collins, K. Howe, and B. Nachman, Anomaly detection for resonant new physics with machine learning, Phys. Rev. Lett. 121, 241803 (2018).
  13. J. H. Collins, K. Howe, and B. Nachman, Extending the search for new resonances with machine learning, Phys. Rev. D 99, 014038 (2019).
  14. R. T. D’Agnolo and A. Wulzer, Learning new physics from a machine, Phys. Rev. D 99, 015014 (2019).
  15. R. T. D’Agnolo, G. Grosso, M. Pierini, A. Wulzer, and M. Zanetti, Learning multivariate new physics, Eur. Phys. J. C 81, 89 (2021).
  16. A. Andreassen, B. Nachman, and D. Shih, Simulation assisted likelihood-free anomaly detection, Phys. Rev. D 101, 095004 (2020).
  17. B. Nachman and D. Shih, Anomaly detection with density estimation, Phys. Rev. D 101, 075042 (2020).
  18. K. Benkendorfer, L. Le Pottier, and B. Nachman, Simulation-assisted decorrelation for resonant anomaly detection, Phys. Rev. D 104, 035003 (2021).
  19. A. Hallin, J. Isaacson, G. Kasieczka, C. Krause, B. Nachman, T. Quadfasel, M. Schlaffer, D. Shih, and M. Sommerhalder, Classifying anomalies through outer density estimation (CATHODE), Phys. Rev. D 106, 055006 (2022).
  20. R. T. d’Agnolo, G. Grosso, M. Pierini, A. Wulzer, and M. Zanetti, Learning new physics from an imperfect machine, Eur. Phys. J. C 82, 275 (2022).
  21. T. Golling, S. Klein, R. Mastandrea, and B. Nachman, Flow-enhanced transportation for anomaly detection, Phys. Rev. D 107, 096025 (2023).
  22. A. Hallin, G. Kasieczka, T. Quadfasel, D. Shih, and M. Sommerhalder, Resonant anomaly detection without background sculpting, Phys. Rev. D 107, 114012 (2023).
  23. T. Golling, G. Kasieczka, C. Krause, R. Mastandrea, B. Nachman, J. A. Raine, D. Sengupta, D. Shih, and M. Sommerhalder, The interplay of machine learning-based resonant anomaly detection methods, Eur. Phys. J. C 84, 241 (2024).
  24. D. Sengupta, S. Klein, J. A. Raine, and T. Golling, CURTAINs flows for flows: Constructing unobserved regions with maximum likelihood estimation, SciPost Phys. 17, 046 (2024).
  25. T. Finke, M. Hein, G. Kasieczka, M. Krämer, A. Mück, P. Prangchaikul, T. Quadfasel, D. Shih, and M. Sommerhalder, Tree-based algorithms for weakly supervised anomaly detection, Phys. Rev. D 109, 034033 (2024).
  26. M. Freytsis, M. Perelstein, and Y. C. San, Anomaly detection in the presence of irrelevant features, J. High Energy Phys. 02 (2024) 220.
  27. E. Buhmann, C. Ewen, G. Kasieczka, V. Mikuni, B. Nachman, and D. Shih, Full phase space resonant anomaly detection, Phys. Rev. D 109, 055015 (2024).
  28. K. Cranmer, J. Pavez, and G. Louppe, Approximating likelihood ratios with calibrated discriminative classifiers, arXiv:1506.02169.
  29. P. Baldi, K. Cranmer, T. Faucett, P. Sadowski, and D. Whiteson, Parameterized neural networks for high-energy physics, Eur. Phys. J. C 76, 235 (2016).
  30. S. E. Park, D. Rankin, S.-M. Udrescu, M. Yunus, and P. Harris, Quasi anomalous knowledge: Searching for new physics with embedded knowledge, J. High Energy Phys. 06 (2021) 030.
  31. C. K. Khosa and V. Sanz, Anomaly awareness, SciPost Phys. 15, 053 (2023).
  32. H. Beauchesne, Z.-E. Chen, and C.-W. Chiang, Improving the performance of weak supervision searches using transfer and meta-learning, J. High Energy Phys. 02 (2024) 138.
  33. T. Golling, L. Heinrich, M. Kagan, S. Klein, M. Leigh, M. Osadchy, and J. A. Raine, Masked particle modeling on sets: Towards self-supervised high energy physics foundation models, Mach. Learn. Sci. Tech. 5, 035074 (2024).
  34. V. Mikuni and B. Nachman, Solving key challenges in collider physics with foundation models, Phys. Rev. D 111, L051504 (2025).
  35. V. Mikuni and B. Nachman, Method to simultaneously facilitate all jet physics tasks, Phys. Rev. D 111, 054015 (2025).
  36. R. Das, G. Kasieczka, and D. Shih, Residual ANODE, arXiv:2312.11629.
  37. K. Cranmer, J. Brehmer, and G. Louppe, The frontier of simulation-based inference, Proc. Natl. Acad. Sci. U.S.A. 117, 30055 (2020).
  38. G. Kasieczka, B. Nachman, and D. Shih, Official datasets for LHC Olympics 2020 anomaly detection challenge (Version v6) [Data set] (2019), 10.5281/zenodo.4536624.
  39. T. Sjostrand, S. Mrenna, and P. Z. Skands, pythia6.4 physics and manual, J. High Energy Phys. 05 (2006) 026.
  40. T. Sjöstrand, S. Ask, J. R. Christiansen, R. Corke, N. Desai, P. Ilten, S. Mrenna, S. Prestel, C. O. Rasmussen, and P. Z. Skands, An introduction to pythia8.2, Comput. Phys. Commun. 191 (2015) 159.
  41. J. de Favereau, C. Delaere, P. Demin, A. Giammanco, V. Lemaitre, A. Mertens, and M. Selvaggi (delphes3 Collaboration), delphes3, A modular framework for fast simulation of a generic collider experiment, J. High Energy Phys. 02 (2014) 057.
  42. A. Mertens, New features in delphes3, J. Phys. Conf. Ser. 608, 012045 (2015).
  43. M. Cacciari and G. P. Salam, Dispelling the N3 myth for the kt jet-finder, Phys. Lett. B 641, 57 (2006).
  44. M. Cacciari, G. P. Salam, and G. Soyez, FastJet user manual, Eur. Phys. J. C 72, 1896 (2012).
  45. M. Cacciari, G. P. Salam, and G. Soyez, The anti-kt jet clustering algorithm, J. High Energy Phys. 04 (2008) 063.
  46. J. Thaler and K. Van Tilburg, Identifying boosted objects with N-subjettiness, J. High Energy Phys. 03 (2011) 015.
  47. J. Thaler and K. Van Tilburg, Maximizing boosted top identification by minimizing N-subjettiness, J. High Energy Phys. 02 (2012) 093.

  48. Previous studies have shown that there may be advantages to oversampling the reference [19]—this could be combined with our approach in future studies.

  49. E. M. Metodiev, B. Nachman, and J. Thaler, Classification without labels: Learning from mixed samples in high energy physics, J. High Energy Phys. 10 (2017) 174.
  50. M. Abadi et al., tensorflow: Large-scale machine learning on heterogeneous systems (2015), Software available from tensorflow.org.
  51. D. P. Kingma and J. Ba, adam: A method for stochastic optimization, arXiv:1412.6980.
  52. C. L. Cheng, G. Singh, and B. Nachman, PAWS: Prior-Assisted Weak Supervision, v1.1.0, Zenodo, https://github.com/hep-lbdl/PAWS.

Outline

Information

Phys. Rev. Lett. 135, 021801– Published 7 July, 2025
  • Received 4 June 2024
  • Revised 14 October 2024
  • Accepted 13 May 2025
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