- 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
  • Open Access

Sensitivity to new physics phenomena in anomaly detection: A study of untunable hyperparameters

Fernando Abreu de Souza1,*, Maura Barros1,†, Nuno F. Castro1,‡, Miguel Crispim Romão2,1,§, Céu Neiva3,1,∥, and Rute Pedro4,¶

  • *Contact author: abreurocha@lip.pt
  • †Contact author: maura.barros@cern.ch
  • ‡Contact author: nuno.castro@fisica.uminho.pt
  • §Contact author: miguel.romao@durham.ac.uk
  • ∥Contact author: ceu.neiva11@icloud.com
  • Contact author: rute.pedro@cern.ch
PDF

Phys. Rev. D 113, 035003 – Published 4 February, 2026

DOI: https://doi.org/10.1103/j2m3-wkkp

Abstract

The search for physics beyond the Standard Model (BSM) at collider experiments requires model-independent strategies to avoid missing possible discoveries of unexpected signals. Anomaly detection (AD) techniques offer a promising approach by identifying deviations from the Standard Model (SM) and have been extensively studied. The sensitivity of these methods to untunable hyperparameters has not been systematically compared, however. This study addresses it by investigating four semisupervised AD methods—AutoEncoders, Deep Support Vector Data Description, Histogram-based Outlier Score, and Isolation Forest—trained on simulated SM background events. In this paper, we study the sensitivity of these methods to BSM benchmark signals as a function of these untunable hyperparameters. Such a study is complemented by a proposal of a nonparametric permutation test using signal-agnostic statistics, which can provide a robust statistical assessment.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (71)

  1. John Ellis, Outstanding questions: Physics beyond the standard model, Phil. Trans. R. Soc. A 370, 818 (2012).
  2. DØ Collaboration, Quasi-model-independent search for new physics at large transverse momentum, Phys. Rev. D 64, 012004 (2001).
  3. DØ Collaboration, Quasi-model-independent search for new high pT physics at DØ, Phys. Rev. Lett. 86, 3712 (2001).
  4. CDF Collaboration, Model-independent and quasi-model-independent search for new physics at CDF, Phys. Rev. D 78, 012002 (2008).
  5. CDF Collaboration, Global search for new physics with 2.0/fb at CDF, Phys. Rev. D 79, 011101 (2009).
  6. H1 Collaboration, A general search for new phenomena in ep scattering at HERA, Phys. Lett. B 602, 14 (2004).
  7. H1 Collaboration, A general search for new phenomena at HERA, Phys. Lett. B 674, 257 (2009).
  8. ATLAS Collaboration, A strategy for a general search for new phenomena using data-derived signal regions and its application within the ATLAS experiment, Eur. Phys. J. C 79, 120 (2019).
  9. CMS Collaboration, MUSiC: A model-unspecific search for new physics in proton–proton collisions at s=13  TeV, Eur. Phys. J. C 81, 629 (2021).
  10. G. Kasieczka et al., The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics, Rep. Prog. Phys. 84, 124201 (2021).
  11. 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).
  12. 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).
  13. 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).
  14. ATLAS Collaboration, Weakly supervised anomaly detection for resonant new physics in the dijet final state using proton-proton collisions at s=13  TeV with the ATLAS detector, Phys. Rev. D 112, 072009 (2025).
  15. CMS Collaboration, Model-agnostic search for dijet resonances with anomalous jet substructure in proton-proton collisions at s=13  TeV, Rep. Prog. Phys. 88, 067802 (2025).
  16. CMS Collaboration, Autoencoder-based anomaly detection system for online data quality monitoring of the CMS electromagnetic calorimeter, Comput. Software Big Sci. 8, 11 (2024).
  17. R. Verheyen, Event generation and density estimation with surjective normalizing flows, SciPost Phys. 13, 047 (2022).
  18. 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, Phys. Rev. D 106, 055006 (2022).
  19. G. Stein, U. Seljak, and B. Dai, Unsupervised in-distribution anomaly detection of new physics through conditional density estimation, in Proceedings of the 34th Conference on Neural Information Processing Systems (2020), arXiv:2012.11638.
  20. B. Nachman and D. Shih, Anomaly detection with density estimation, Phys. Rev. D 101, 075042 (2020).
  21. M. Crispim Romão, N. F. Castro, and R. Pedro, Finding new physics without learning about it: Anomaly detection as a tool for searches at colliders, Eur. Phys. J. C 81, 27 (2021).
  22. M. Farina, Y. Nakai, and D. Shih, Searching for new physics with deep autoencoders, Phys. Rev. D 101, 075021 (2020).
  23. A. Banda, C. K. Khosa, and V. Sanz, Strengthening anomaly awareness, arXiv:2504.11520.
  24. S. V. Chekanov, W. Islam, R. Zhang, and N. Luongo, ADFilter—A web tool for new physics searches with autoencoder-based anomaly detection using deep unsupervised neural networks, Information 16, 258 (2025).
  25. M. Crispim Romão, J. G. Milhano, and M. van Leeuwen, Jet substructure observables for jet quenching in quark gluon plasma: A machine learning driven analysis, SciPost Phys. 16, 015 (2024).
  26. T. Heimel, G. Kasieczka, T. Plehn, and J. Thompson, QCD or what?, SciPost Phys. 6, 030 (2019).
  27. T. S. Roy and A. H. Vijay, A robust anomaly finder based on autoencoders, arXiv:1903.02032.
  28. T. Finke, M. Krämer, A. Morandini, A. Mück, and I. Oleksiyuk, Autoencoders for unsupervised anomaly detection in high energy physics, J. High Energy Phys. 06 (2021) 161.
  29. L. Apolinário, N. F. Castro, M. Crispim Romão, J. G. Milhano, R. Pedro, and F. C. R. Peres, Deep Learning for the classification of quenched jets, J. High Energy Phys. 11 (2021) 219.
  30. F. Canelli, A. de Cosa, L. L. Pottier, J. Niedziela, K. Pedro, and M. Pierini, Autoencoders for semivisible jet detection, J. High Energy Phys. 02 (2022) 074.
  31. E. Govorkova, E. Puljak, T. Aarrestad, T. James, V. Loncar, M. Pierini, A. A. Pol, N. Ghielmetti, M. Graczyk, S. Summers, J. Ngadiuba, T. Q. Nguyen, J. Duarte, and Z. Wu, Autoencoders on field-programmable gate arrays for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider, Nat. Mach. Intell. 4, 154 (2022).
  32. B. M. Dillon, L. Favaro, T. Plehn, P. Sorrenson, and M. Krämer, A normalized autoencoder for LHC triggers, SciPostPhys. Core 6, 074 (2023).
  33. B. Bhattacherjee, P. Konar, V. S. Ngairangbam, and P. Solanki, LLPNet: Graph autoencoder for triggering light long-lived particles at HL-LHC, arXiv:2308.13611.
  34. P. Ilten, T. Menzo, A. Youssef, and J. Zupan, Modeling hadronization using machine learning, SciPost Phys. 14, 027 (2023).
  35. M. Touranakou, N. Chernyavskaya, J. Duarte, D. Gunopulos, R. Kansal, B. Orzari, M. Pierini, T. Tomei, and J. Vlimant, Particle-based fast jet simulation at the LHC with variational autoencoders, Mach. Learn. 3, 035003 (2022).
  36. J. Crispim Romão and M. Crispim Romão, Combining evolutionary strategies and novelty detection to go beyond the alignment limit of the Z3 3HDM, Phys. Rev. D 109, 095040 (2024).
  37. F. A. de Souza, N. F. Castro, M. Crispim Romão, and W. Porod, Exploring scotogenic parameter spaces and mapping uncharted dark matter phenomenology with multi-objective search algorithms, J. High Energy Phys. 10 (2025) 116.
  38. F. A. de Souza, R. Boto, M. Crispim Romão, P. N. Figueiredo, J. Crispim Romão, and J. P. Silva, Unearthing large pseudoscalar Yukawa couplings with Machine Learning, J. High Energy Phys. 07 (2025) 268.
  39. S. Caron, J. E. García Navarro, M. M. Llácer, P. Moskvitina, M. Rovers, A. R. Jímenez, R. Ruiz de Austri, and Z. Zhang, Universal anomaly detection at the LHC: Transforming optimal classifiers and the DDD method, Eur. Phys. J. C 85, 415 (2025).
  40. C. L. Cheng, G. Singh, and B. Nachman, Incorporating physical priors into weakly-supervised anomaly detection, Phys. Rev. Lett. 135, 021801 (2025).
  41. L. Brennan, T. A. Vami, O. Amram, S. Sekhar, Y. Takahashi, L. Moureaux, M. Sommerhalder, P. Maksimovic, and T. Cai, Weakly supervised anomaly detection with event-level variables, Phys. Rev. D 112, 055040 (2025).
  42. K. Metzger, L. Xu, M. Sodini, T. K. Arrestad, K. Govorkova, G. Grosso, and P. Harris, Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC, Phys. Rev. D 112, 072011 (2025).
  43. V. S. Ngairangbam, B. Rozwoda, K. Sakurai, and M. Spannowsky, Enhancing anomaly detection with topology-aware autoencoders, Mach. Learn. Sci. Tech. 6, 045051 (2025).
  44. V. Sanz, Learning symmetries in datasets, arXiv:2504.05174.
  45. G. Grosso and M. Letizia, Multiple testing for signal-agnostic searches of new physics with machine learning, Eur. Phys. J. C 85, 4 (2025).
  46. G. Grosso, M. Letizia, M. Pierini, and A. Wulzer, Goodness of fit by Neyman-Pearson testing, SciPost Phys. 16, 123 (2024).
  47. J. Alwall, R. Frederix, S. Frixione, V. Hirschi, F. Maltoni, O. Mattelaer, H.-S. Shao, T. Stelzer, P. Torrielli, and M. Zaro, The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations, J. High Energy Phys. 07 (2014) 079.
  48. T. Söstrand, 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 pythia 8.2, Comput. Phys. Commun. 191, 159 (2015).
  49. J. de Favereau, C. Delaere, P. Demin, A. Giammanco, V. Lemaître, A. Mertens, and M. Selvaggi (delphes 3 collaboration), A modular framework for fast simulation of a generic collider experiment, J. High Energy Phys. 02 (2014) 057.
  50. M. Cacciari, G. P. Salam, and G. Soyez, The anti-kt jet clustering algorithm, J. High Energy Phys. 04 (2008) 063.
  51. ATLAS Collaboration, Combination of the searches for pair-produced vectorlike partners of the third-generation quarks at s=13  TeV with the ATLAS detector, Phys. Rev. Lett. 121, 211801 (2018).
  52. G. Durieux, F. Maltoni, and C. Zhang, Global approach to top-quark flavor-changing interactions, Phys. Rev. D 91, 074017 (2015).
  53. L. Randall and R. Sundrum, Large mass hierarchy from a small extra dimension, Phys. Rev. Lett. 83, 3370 (1999).
  54. ATLAS Collaboration, Search for heavy Higgs bosons with flavour-violating couplings in multi-lepton plus b-jets final states in pp collisions at 13 TeV with the ATLAS detector, J. High Energy Phys. 12 (2023) 081.
  55. ATLAS Collaboration, Search for heavy Majorana or Dirac neutrinos and right-handed W gauge bosons in final states with charged leptons and jets in pp collisions at s=13  TeV with the ATLAS detector, Eur. Phys. J. C 83, 1164 (2023).
  56. M. Crispim Romao, N. F. Castro, and R. Pedro, Simulated pp collisions at 13 TeV with 2 leptons + 1 b jet final state and selected benchmark Beyond the Standard Model signals, 10.5281/zenodo.5126747 (2021).
  57. F. Abreu de Souza, M. Barros, N. F. Castro, M. Crispim Romão, and R. Pedro, Simulated pp collisions at 13 TeV for Standard Model background and beyond Standard Model signals with 2 leptons, 1-bjet and high HT, 10.5281/zenodo.15423467 (2025).
  58. Jesse Thaler and Ken Van Tilburg, Identifying boosted objects with N-subjettiness, J. High Energy Phys. 03 (2011) 015.
  59. M. Goldstein and A. Dengel, Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm (2012), https://www.goldiges.de/publications/HBOS-KI-2012.pdf.
  60. F. T. Liu, K. M. Ting, and Z. Zhou, Isolation forest, in 2008 Eighth IEEE International Conference on Data Mining (2008), pp. 413–422, https://ieeexplore.ieee.org/document/4781136.
  61. L. Ruff, R. Vandermeulen, N. Goernitz, L. Deecke, S. A. Siddiqui, A. Binder, E. Müller, and M. Kloft, Deep one-class classification, in Proceedings of the 35th International Conference on Machine Learning, edited by Jennifer Dy and Andreas Krause, Volume 80 of Proceedings of Machine Learning Research (PMLR, 2018), pp. 4393–4402, https://proceedings.mlr.press/v80/ruff18a.html.
  62. M. Crispim Romao, D. Croon, and D. Godines, Anomaly detection to identify transients in LSST time series data, Mon. Not. R. Astron. Soc. 351, 357 (2025).
  63. Y. Zhao, Z. Nasrullah, and Z. Li, pyod: A python toolbox for scalable outlier detection, J. Mach. Learn. Res. 20, 1 (2019), arXiv:1901.01588.
  64. F. Pedregosa et al., scikit-learn: Machine learning in python, J. Mach. Learn. Res. 12, 2825 (2011), arXiv:1201.0490.
  65. M. Abadi et al., tensorflow: Large-scale machine learning on heterogeneous distributed systems, arXiv:1603.04467.
  66. T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, optuna: A next-generation hyperparameter optimization framework, in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’19 (Association for Computing Machinery, New York, NY, USA, 2019), pp. 2623–2631, 10.1145/3292500.3330701.
  67. A. N. Kolmogorov-Smirnov, Sulla determinazione empírica di una legge di distribuzione (1933), Vol. 4, pp. 83–91, https://api.semanticscholar.org/CorpusID:222427298.
  68. N. V. Smirnov, Table for Estimating the Goodness of Fit of Empirical Distributions, Ann. Math. Stat. 19, 279 (1948).
  69. L. Baringhaus and C. Franz, On a new multivariate two-sample test, J. Multivariate Anal. 88, 190 (2004).
  70. H. Cramér, On the composition of elementary errors, Scand. Actuarial J. 1928, 13 (1928).
  71. D. Wolpert, The lack of a priori distinctions between learning algorithms, Neural Comput. 8, 1341 (1996).

Outline

Information

Phys. Rev. D 113, 035003– Published 4 February, 2026
  • Received 28 May 2025
  • Accepted 2 January 2026
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