- 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

Single interpolated generative model for anomalies

Ranit Das* and David Shih†

  • NHETC, Department of Physics and Astronomy, Rutgers University, Piscataway, New Jersey 08854, USA

  • *Contact author: ranit@physics.rutgers.edu
  • †Contact author: shih@physics.rutgers.edu
PDF

Phys. Rev. D 112, 074040 – Published 29 October, 2025

DOI: https://doi.org/10.1103/rj53-2x6j

Abstract

A key step in any resonant anomaly detection search is accurate modeling of the background distribution in each signal region. Data-driven methods like CATHODE accomplish this by training separate generative models on the complement of each signal region, and interpolating them into their corresponding signal regions. Having to retrain the generative model on essentially the entire dataset for each signal region is a major computational cost in a typical sliding window search with many signal regions. Here, we present SIGMA, a new, fully data-driven, computationally efficient method for estimating background distributions. The idea is to train a single generative model on all of the data and interpolate its parameters in sideband regions in order to obtain a model for the background in the signal region. The SIGMA method significantly reduces the computational cost compared to previous approaches, while retaining a similar high quality of background modeling and sensitivity to anomalous signals.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (99)

  1. J. H. Collins, K. Howe, and B. Nachman, Phys. Rev. Lett. 121, 241803 (2018).
  2. J. H. Collins, K. Howe, and B. Nachman, Phys. Rev. D 99, 014038 (2019).
  3. B. Nachman and D. Shih, Phys. Rev. D 101, 075042 (2020).
  4. A. Andreassen, B. Nachman, and D. Shih, Phys. Rev. D 101, 095004 (2020).
  5. G. Stein, U. Seljak, and B. Dai, in Proceedings of the 34th Conference on Neural Information Processing Systems (2020).
  6. O. Amram and C. M. Suarez, J. High Energy Phys. 01 (2021) 153.
  7. A. Hallin, J. Isaacson, G. Kasieczka, C. Krause, B. Nachman, T. Quadfasel, M. Schlaffer, D. Shih, and M. Sommerhalder, Phys. Rev. D 106, 055006 (2022).
  8. J. H. Collins, P. Martín-Ramiro, B. Nachman, and D. Shih, Eur. Phys. J. C 81, 617 (2021).
  9. K. Benkendorfer, L. L. Pottier, and B. Nachman, Phys. Rev. D 104, 035003 (2020).
  10. G. Kasieczka, B. Nachman, and D. Shih, arXiv:2107.02821.
  11. A. Hallin, G. Kasieczka, T. Quadfasel, D. Shih, and M. Sommerhalder, Phys. Rev. D 107, 114012 (2023).
  12. M. F. Chen, B. Nachman, and F. Sala, J. High Energy Phys. 07 (2023) 188.
  13. J. F. Kamenik and M. Szewc, Phys. Lett. B 840, 137836 (2023).
  14. D. Sengupta, S. Klein, J. A. Raine, and T. Golling, SciPost Phys. 17, 046 (2024).
  15. J. A. Raine, S. Klein, D. Sengupta, and T. Golling, Front. Big Data 6, 899345 (2023).
  16. T. Golling, G. Kasieczka, C. Krause, R. Mastandrea, B. Nachman, J. A. Raine, D. Sengupta, D. Shih, and M. Sommerhalder, Eur. Phys. J. C 84, 241 (2024).
  17. T. Golling, S. Klein, R. Mastandrea, and B. Nachman, Phys. Rev. D 107, 096025 (2023).
  18. G. Bickendorf, M. Drees, G. Kasieczka, C. Krause, and D. Shih, Phys. Rev. D 109, 096031 (2024).
  19. T. Finke, M. Hein, G. Kasieczka, M. Krämer, A. Mück, P. Prangchaikul, T. Quadfasel, D. Shih, and M. Sommerhalder, Phys. Rev. D 109, 034033 (2024).
  20. M. Freytsis, M. Perelstein, and Y. C. San, J. High Energy Phys. 02 (2024) 220.
  21. E. Buhmann, C. Ewen, G. Kasieczka, V. Mikuni, B. Nachman, and D. Shih, Phys. Rev. D 109, 055015 (2024).
  22. R. Das, G. Kasieczka, and D. Shih, arXiv:2312.11629.
  23. H. Beauchesne, Z.-E. Chen, and C.-W. Chiang, J. High Energy Phys. 02 (2024) 138.
  24. D. Sengupta, M. Leigh, J. A. Raine, S. Klein, and T. Golling, J. High Energy Phys. 04 (2024) 109.
  25. G. Kasieczka et al., Rep. Prog. Phys. 84, 124201 (2021).
  26. D. Sengupta, S. Klein, J. A. Raine, and T. Golling, SciPost Phys. 17, 046 (2024).
  27. R. Mastandrea and B. Nachman, in Proceedings of the 36th Conference on Neural Information Processing Systems (2022).
  28. C. L. Cheng, G. Singh, and B. Nachman, Phys. Rev. Lett. 135, 021801 (2025).
  29. K. Benkendorfer, L. Le Pottier, and B. Nachman, Phys. Rev. D 104, 035003 (2021).
  30. M. Leigh, D. Sengupta, B. Nachman, and T. Golling, arXiv:2407.19818.
  31. C. Li et al., arXiv:2405.12972.
  32. G. Aad et al. (ATLAS Collaboration), Phys. Rev. Lett. 125, 131801 (2020).
  33. CMS CollaborationModel-agnostic search for dijet resonances with anomalous jet substructure in proton-proton collisions at s=13  TeV, Technical Report No. CMS-EXO-22-026, CERN-EP-2024-291 (CERN, Geneva, 2024).
  34. D. Shih, M. R. Buckley, L. Necib, and J. Tamanas, Mon. Not. R. Astron. Soc. 509, 5992 (2021).
  35. D. Shih, M. R. Buckley, and L. Necib, Mon. Not. R. Astron. Soc. 529, 4745 (2024).
  36. M. Pettee, S. Thanvantri, B. Nachman, D. Shih, M. R. Buckley, and J. H. Collins, Mon. Not. R. Astron. Soc. 527, 8459 (2023).
  37. D. Sengupta, S. Mulligan, D. Shih, J. A. Raine, and T. Golling, Mon. Not. R. Astron. Soc. 536, 1104 (2024).
  38. R. Das, L. Favaro, T. Heimel, C. Krause, T. Plehn, and D. Shih, SciPost Phys. 16, 031 (2024).
  39. G. Kasieczka, B. Nachman, and D. Shih, R&D Dataset for LHC Olympics 2020 Anomaly Detection Challenge (2022)https://doi.org/10.5281/zenodo.6466204.
  40. G. Kasieczka, B. Nachman, D. Shih et al., Rep. Prog. Phys. 84, 124201 (2021).
  41. T. Sjöstrand, S. Mrenna, and P. Skands, J. High Energy Phys. 05 (2006) 026.
  42. T. Sjöstrand, S. Mrenna, and P. Skands, Comput. Phys. Commun. 178, 852 (2008).
  43. J. de Favereau, C. Delaere, P. Demin, A. Giammanco, V. Lemaître, A. Mertens, and M. Selvaggi, J. High Energy Phys. 02 (2014) 057.
  44. A. Mertens, J. Phys. Conf. Ser. 608, 012045 (2015).
  45. M. Selvaggi, J. Phys. Conf. Ser. 523, 012033 (2014).
  46. M. Cacciari and G. P. Salam, Phys. Lett. B 641, 57 (2006).
  47. M. Cacciari, G. P. Salam, and G. Soyez, J. High Energy Phys. 04 (2008) 063.
  48. M. Cacciari, G. P. Salam, and G. Soyez, Eur. Phys. J. C 72, 1896 (2012).
  49. J. Thaler and K. Van Tilburg, J. High Energy Phys. 03 (2011) 015.
  50. J. Thaler and K. Van Tilburg, J. High Energy Phys. 02 (2012) 093.
  51. J. A. Raine, S. Klein, D. Sengupta, and T. Golling, Front. Big Data 6, 89934 (2023).
  52. D. Shih, Additional QCD Background Events for LHCO2020 R&D (signal region only) (2021).
  53. Y. Lipman, R. T. Q. Chen, H. Ben-Hamu, M. Nickel, and M. Le, arXiv:2210.02747.
  54. A. Tong, K. Fatras, N. Malkin, G. Huguet, Y. Zhang, J. Rector-Brooks, G. Wolf, and Y. Bengio, arXiv:2302.00482.
  55. A.-A. Pooladian, H. Ben-Hamu, C. Domingo-Enrich, B. Amos, Y. Lipman, and R. T. Q. Chen, arXiv:2304.14772.
  56. X. Liu, C. Gong, and Q. Liu, arXiv:2209.03003.
  57. M. S. Albergo and E. Vanden-Eijnden, arXiv:2209.15571.
  58. J. Ho, A. Jain, and P. Abbeel, arXiv:2006.11239.
  59. R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022), pp. 10684–10695.
  60. T. Karras, M. Aittala, T. Aila, and S. Laine, Adv. Neural Inf. Process. Syst. 35, 26565 (2022), arXiv:2206.00364.
  61. P. Dhariwal and A. Nichol, Adv. Neural Inf. Process. Syst. 34, 8780 (2021), arXiv:2105.05233.
  62. Y. Song and S. Ermon, Adv. Neural Inf. Process. Syst. 32 (2019), arXiv:1907.05600.
  63. V. Mikuni and B. Nachman, Phys. Rev. D 106, 092009 (2022).
  64. V. Mikuni and B. Nachman, J. Instrum. 19, P02001 (2024).
  65. A. Ramesh, M. Pavlov, G. Goh, S. Gray, C. Voss, A. Radford, M. Chen, and I. Sutskever, in International Conference on Machine Learning (Pmlr, 2021), pp. 8821–8831.
  66. A. Ramesh, P. Dhariwal, A. Nichol, C. Chu, and M. Chen, arXiv:2204.06125.
  67. J. Birk, E. Buhmann, C. Ewen, G. Kasieczka, and D. Shih, Phys. Rev. D 111, 052008 (2025).
  68. E. Buhmann, C. Ewen, D. A. Faroughy, T. Golling, G. Kasieczka, M. Leigh, G. Quétant, J. A. Raine, D. Sengupta, and D. Shih, arXiv:2310.00049.
  69. L. Favaro, A. Ore, S. Palacios Schweitzer, and T. Plehn, SciPost Phys. 18, 088 (2025).
  70. A. Butter, T. Jezo, M. Klasen, M. Kuschick, S. Palacios Schweitzer, and T. Plehn, SciPost Phys. Core 7, 064 (2024).
  71. J. Birk, A. Hallin, and G. Kasieczka, Mach. Learn. Sci. Tech. 5, 035031 (2024).
  72. F. Vaselli, F. Cattafesta, P. Asenov, and A. Rizzi, Mach. Learn. Sci. Tech. 5, 035007 (2024).
  73. T. Heimel, N. Huetsch, R. Winterhalder, T. Plehn, and A. Butter, SciPost Phys. 17, 129 (2024).
  74. V. Mikuni and B. Nachman, Phys. Rev. D 111, L051504 (2025).
  75. S. Bieringer, G. Kasieczka, J. Kieseler, and M. Trabs, Eur. Phys. J. C 84, 972 (2024).
  76. A. Butter, N. Huetsch, S. Palacios Schweitzer, T. Plehn, P. Sorrenson, and J. Spinner, SciPost Phys. Core 8, 026 (2025).
  77. N. Huetsch et al., SciPost Phys. 18, 070 (2025).
  78. E. Buhmann, S. Diefenbacher, E. Eren, F. Gaede, G. Kasieczka, A. Korol, W. Korcari, K. Krüger, and P. McKeown, J. Instrum. 18, P11025 (2023).
  79. E. Buhmann, F. Gaede, G. Kasieczka, A. Korol, W. Korcari, K. Krüger, and P. McKeown, J. Instrum. 19, P04020 (2024).
  80. V. Mikuni and B. Nachman, SciPost Phys. 16, 062 (2024).
  81. A. Shmakov, K. T. Greif, M. J. Fenton, A. Ghosh, P. Baldi, and D. Whiteson, SciPost Phys. 18, 117 (2025).
  82. B. Hashemi and C. Krause, Rev. Phys. 12, 100092 (2024).
  83. D. Sengupta, M. Leigh, J. A. Raine, S. Klein, and T. Golling, J. High Energy Phys. 04 (2024) 109.
  84. P. Devlin, J.-W. Qiu, F. Ringer, and N. Sato, Phys. Rev. D 110, 016030 (2024).
  85. O. Amram and K. Pedro, Phys. Rev. D 108, 072014 (2023).
  86. Z. Imani, T. Wongjirad, and S. Aeron, Phys. Rev. D 109, 072011 (2024).
  87. M. Leigh, D. Sengupta, J. A. Raine, G. Quétant, and T. Golling, Phys. Rev. D 109, 012010 (2024).
  88. R. T. Q. Chen, Y. Rubanova, J. Bettencourt, and D. Duvenaud, arXiv:1806.07366.
  89. K. He, X. Zhang, S. Ren, and J. Sun, arXiv:1512.03385.
  90. C. Durkan, A. Bekasov, I. Murray, and G. Papamakarios, nflows: Normalizing flows in PyTorch (2020).
  91. A. Hallin, G. Kasieczka, T. Quadfasel, D. Shih, and M. Sommerhalder, Phys. Rev. D 107, 114012 (2023).
  92. B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, and R. Ng, arXiv:2003.08934.
  93. N. Rahaman, A. Baratin, D. Arpit, F. Draxler, M. Lin, F. A. Hamprecht, Y. Bengio, and A. Courville, arXiv:1806.08734.
  94. A. Paszke et al., arXiv:1912.01703.
  95. I. Loshchilov and F. Hutter, arXiv:1711.05101.
  96. F. Rozet et al., Zuko: Normalizing flows in pytorch (2022), https://doi.org/10.5281/zenodo.7625672.
  97. J. Zhuang, N. Dvornek, X. Li, S. Tatikonda, X. Papademetris, and J. Duncan, arXiv:2006.02493.
  98. https://it.rutgers.edu/oarc.
  99. R. Das, Sigma: Single interpolated generative model for anomalies (2024), https://github.com/rd804/SIGMA.

Outline

Information

Phys. Rev. D 112, 074040– Published 29 October, 2025
  • Received 8 April 2025
  • Accepted 25 September 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