- 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

Unbinned inclusive cross-section measurements with machine-learned systematic uncertainties

Lisa Benato, Cristina Giordano, Claudius Krause, Ang Li, Robert Schöfbeck, Dennis Schwarz, Maryam Shooshtari, and Daohan Wang

PDF

Phys. Rev. D 112, 052006 – Published 18 September, 2025

DOI: https://doi.org/10.1103/zwzt-1rrw

Abstract

We introduce a novel methodology for addressing systematic uncertainties in unbinned inclusive cross-section measurements and related collider-based inference problems. Our approach incorporates known analytic dependencies on parameters of interest, including signal strengths and nuisance parameters. When these dependencies are unknown, as is frequently the case for systematic uncertainties, dedicated neural network parametrizations provide an approximation that is trained on simulated data. The resulting machine-learned surrogate captures the complete parameter dependence of the likelihood ratio, providing a near-optimal test statistic. As a case study, we perform a first-principles inclusive cross-section measurement of H→ττ in the single-lepton channel, utilizing simulated data from the FAIR universe Higgs uncertainty challenge. Results in Asimov data, from large-scale toy studies, and using the Fisher information demonstrate significant improvements over traditional binned methods. Our computer code guaranteed optimal log-likelihood-based unbinned method (GOLLUM) for machine-learning and inference is publicly available.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (56)

  1. Lyndon Evans and Philip Bryant, LHC machine, J. Instrum. 3, S08001 (2008).
  2. Glen Cowan, Kyle Cranmer, Eilam Gross, and Ofer Vitells, Asymptotic formulae for likelihood-based tests of new physics, Eur. Phys. J. C 71, 1554 (2011); 73, 2501(E) (2013).
  3. The ATLAS and CMS Collaborations and The LHC Higgs Combination Group, Procedure for the LHC Higgs boson search combination in Summer 2011, https://cds.cern.ch/record/1379837.
  4. Kyle Cranmer, Practical statistics for the LHC, in Proceedings of the 2011 European School of High-Energy Physics (2014), p. 267, arXiv:1503.07622.
  5. CMS Collaboration, The CMS statistical analysis and combination tool: combine, Comput. Software Big Sci. 8, 19 (2024).
  6. Johann Brehmer, Kyle Cranmer, Gilles Louppe, and Juan Pavez, Constraining effective field theories with machine learning, Phys. Rev. Lett. 121, 111801 (2018).
  7. Johann Brehmer, Kyle Cranmer, Gilles Louppe, and Juan Pavez, A guide to constraining effective field theories with machine learning, Phys. Rev. D 98, 052004 (2018).
  8. Johann Brehmer, Gilles Louppe, Juan Pavez, and Kyle Cranmer, Mining gold from implicit models to improve likelihood-free inference, Proc. Natl. Acad. Sci. U.S.A. 117, 5242 (2020).
  9. Johann Brehmer, Felix Kling, Irina Espejo, and Kyle Cranmer, MadMiner: Machine learning-based inference for particle physics, Comput. Software Big Sci. 4, 3 (2020).
  10. Kyoungchul Kong, Konstantin T. Matchev, Stephen Mrenna, and Prasanth Shyamsundar, New machine learning techniques for simulation-based inference: InferoStatic nets, kernel score estimation, and kernel likelihood ratio estimation, arXiv:2210.01680.
  11. Kyle Cranmer, Johann Brehmer, and Gilles Louppe, The frontier of simulation-based inference, Proc. Natl. Acad. Sci. U.S.A. 117, 30055 (2020).
  12. Henning Bahl, Victor Bresó, Giovanni De Crescenzo, and Tilman Plehn, Advancing tools for simulation-based inference, arXiv:2410.07315.
  13. Johann Brehmer, Sally Dawson, Samuel Homiller, Felix Kling, and Tilman Plehn, Benchmarking simplified template cross sections in WH production, J. High Energy Phys. 11 (2019) 034.
  14. Rahool Kumar Barman, Dorival Gonçalves, and Felix Kling, Machine learning the Higgs boson-top quark CP phase, Phys. Rev. D 105, 035023 (2022).
  15. Henning Bahl and Simon Brass, Constraining CP-violation in the Higgs-top-quark interaction using machine-learning-based inference, J. High Energy Phys. 03 (2022) 017.
  16. Raquel Gomez Ambrosio, Jaco ter Hoeve, Maeve Madigan, Juan Rojo, and Veronica Sanz, Unbinned multivariate observables for global SMEFT analyses from machine learning, J. High Energy Phys. 03 (2023) 033.
  17. Ricardo Barrué, Patricia Conde-Muíño, Valerio Dao, and Rui Santos, Simulation-based inference in the search for CP violation in leptonic WH production, J. High Energy Phys. 04 (2024) 014.
  18. Radha Mastandrea, Benjamin Nachman, and Tilman Plehn, Constraining the Higgs potential with neural simulation-based inference for di-Higgs production, Phys. Rev. D 110, 056004 (2024).
  19. Chi Lung Cheng, Gup Singh, and Benjamin Nachman, Incorporating physical priors into weakly supervised anomaly detection, Phys. Rev. Lett. 135, 021801 (2025).
  20. Chi Lung Cheng, Ranit Das, Runze Li, Radha Mastandrea, Vinicius Mikuni, Benjamin Nachman, David Shih, and Gup Singh, Generator based inference (GBI), arXiv:2506.00119.
  21. Robert Schöfbeck, Refinable modeling for unbinned SMEFT analyses, Mach. Learn. Sci. Tech. 6, 015007 (2025).
  22. Wahid Bhimji et al., FAIR universe HiggsML uncertainty challenge competition, arXiv:2410.02867.
  23. Lisa Benato, Cristina Giordano, Claudius Krause, Ang Li, Robert Schöfbeck, Dennis Schwarz, Maryam Shooshtari, and Daohan Wang, gollum Code repository, https://github.com/HephyAnalysisSW/GOLLUM (2025).
  24. ATLAS Collaboration, The ATLAS experiment at the CERN large hadron collider, J. Instrum. 3, S08003 (2008).
  25. ATLAS Collaboration, An implementation of neural simulation-based inference for parameter estimation in ATLAS, Rep. Prog. Phys. 88, 067801 (2025).
  26. Georges Aad et al., Measurement of off-shell Higgs boson production in the H*→ZZ→4ℓ decay channel using a neural simulation-based inference technique in 13 TeV pp collisions with the ATLAS detector, Rep. Prog. Phys. 88, 057803 (2025).
  27. CMS Collaboration, The CMS experiment at the CERN LHC, J. Instrum. 3, S08004 (2008).
  28. CMS Collaboration, Search for neutral Higgs bosons decaying to tau pairs in pp collisions at s=7  TeV, Phys. Lett. B 713, 68 (2012).
  29. ATLAS Collaboration, Search for the standard model Higgs boson in the H to τ+τ− decay mode in s=7  TeV pp collisions with ATLAS, J. High Energy Phys. 09 (2012) 070.
  30. CMS Collaboration, Evidence for the 125 GeV Higgs boson decaying to a pair of τ leptons, J. High Energy Phys. 05 (2014) 104.
  31. ATLAS Collaboration, Evidence for the Higgs-boson Yukawa coupling to tau leptons with the ATLAS detector, J. High Energy Phys. 04 (2015) 117.
  32. CMS Collaboration, Observation of the Higgs boson decay to a pair of τ leptons with the CMS detector, Phys. Lett. B 779, 283 (2018).
  33. ATLAS Collaboration, Cross-section measurements of the Higgs boson decaying into a pair of τ-leptons in proton-proton collisions at s=13  TeV with the ATLAS detector, Phys. Rev. D 99, 072001 (2019).
  34. CMS Collaboration, Measurements of Higgs boson production in the decay channel with a pair of τ leptons in proton–proton collisions at s=13  TeV, Eur. Phys. J. C 83, 562 (2023).
  35. ATLAS Collaboration, Measurements of Higgs boson production cross sections in the H→τ+τ− decay channel in pp collisions at s=13  TeV with the ATLAS detector, J. High Energy Phys. 08 (2022) 175.
  36. CMS Collaboration, Measurement of the inclusive and differential Higgs boson production cross sections in the decay mode to a pair of τ leptons in pp collisions at s=13  TeV, Phys. Rev. Lett. 128, 081805 (2022).
  37. CMS Collaboration, Measurement of the production cross section of a Higgs boson with large transverse momentum in its decays to a pair of τ leptons in proton-proton collisions at s=13  TeV, Phys. Lett. B 857, 138964 (2024).
  38. ATLAS Collaboration, Differential cross-section measurements of Higgs boson production in the H τ+τ− decay channel in pp collisions at s=13  TeV with the ATLAS detector, J. High Energy Phys. 03 (2025) 010.
  39. Torbjörn Sjöstrand, Stefan Ask, Jesper R. Christiansen, Richard Corke, Nishita Desai, Philip Ilten, Stephen Mrenna, Stefan Prestel, Christine O. Rasmussen, and Peter Z. Skands, An introduction to pythia 8.2, Comput. Phys. Commun. 191, 159 (2015).
  40. J. de Favereau, C. Delaere, P. Demin, A. Giammanco, V. Lemaître, A. Mertens, and M. Selvaggi, delphes 3, a modular framework for fast simulation of a generic collider experiment, J. High Energy Phys. 02 (2014) 057.
  41. Jerzy Neyman and Egon Sharpe Pearson, On the problem of the most efficient tests of statistical hypotheses, Phil. Trans. R. Soc. A 231, 289 (1933).
  42. S. S. Wilks, The large-sample distribution of the likelihood ratio for testing composite hypotheses, Ann. Math. Stat. 9, 60 (1938).
  43. Roger J. Barlow, Extended maximum likelihood, Nucl. Instrum. Methods Phys. Res., Sect. A 297, 496 (1990).
  44. Charles R. Harris, K. Jarrod Millman, Stéfan J. van der Walt, Ralf Gommers, Pauli Virtanen, and David Cournapeau et al., Array programming with numpy, Nature (London) 585, 357 (2020).
  45. Pauli Virtanen, Ralf Gommers, Travis E. Oliphant, Matt Haberland, and Tyler Reddy et al., scipy 1.0: Fundamental algorithms for scientific computing in python, Nat. Methods 17, 261 (2020).
  46. Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, and Zhifeng Chen et al., tensorflow: Large-scale machine learning on heterogeneous systems, 2015, Software available from https://www.tensorflow.org/.
  47. Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger, On calibration of modern neural networks, arXiv:1706.04599.
  48. Kyle Cranmer, Juan Pavez, and Gilles Louppe, Approximating likelihood ratios with calibrated discriminative classifiers, arXiv:1506.02169.
  49. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion et al., Scikit-learn: Machine learning in python, J. Mach. Learn. Res. 12, 2825 (2011).
  50. F. James and M. Roos, minuit: A system for function minimization and analysis of the parameter errors and correlations, Comput. Phys. Commun. 10, 343 (1975).
  51. C. R. Rao, Information and the accuracy attainable in the estimation of statistical parameters, Bull. Calcutta Math. Soc. 37, 81 (1945).
  52. H. Cramér, Mathematical Methods of Statistics (Princeton University Press, Princeton, NJ, 1946).
  53. https://www.clip.science/.
  54. L. Benato, C. Giordano, C. Krause, A. Li, R. Schoefbeck, D. Schwarz, M. Shooshtari, and D. Wang, Training Data for Gollum in Higgs Uncertainty Challenge (Zenodo, 2025), 10.5281/zenodo.15322773.
  55. W. Bhimji et al., FAIR Universe—HiggsML Uncertainty Challenge Public Dataset (Zenodo, 2025), 10.5281/zenodo.15131565.
  56. Abraham Wald, Tests of statistical hypotheses concerning several parameters when the number of observations is large, Trans. Am. Math. Soc. 54, 426 (1943).

Outline

Information

Phys. Rev. D 112, 052006– Published 18 September, 2025
  • Received 22 May 2025
  • Accepted 22 July 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