Home > Research > Publications & Outputs > An implementation of neural simulation-based in...

Associated organisational unit

Links

Text available via DOI:

View graph of relations

An implementation of neural simulation-based inference for parameter estimation in ATLAS

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

An implementation of neural simulation-based inference for parameter estimation in ATLAS. / The ATLAS collaboration.
In: Reports on Progress in Physics, Vol. 88, No. 6, 067801, 27.05.2025.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

The ATLAS collaboration 2025, 'An implementation of neural simulation-based inference for parameter estimation in ATLAS', Reports on Progress in Physics, vol. 88, no. 6, 067801. https://doi.org/10.1088/1361-6633/add370

APA

The ATLAS collaboration (2025). An implementation of neural simulation-based inference for parameter estimation in ATLAS. Reports on Progress in Physics, 88(6), Article 067801. https://doi.org/10.1088/1361-6633/add370

Vancouver

The ATLAS collaboration. An implementation of neural simulation-based inference for parameter estimation in ATLAS. Reports on Progress in Physics. 2025 May 27;88(6):067801. doi: 10.1088/1361-6633/add370

Author

The ATLAS collaboration. / An implementation of neural simulation-based inference for parameter estimation in ATLAS. In: Reports on Progress in Physics. 2025 ; Vol. 88, No. 6.

Bibtex

@article{16dda8f57f7443b9994a0dd06844ce3d,
title = "An implementation of neural simulation-based inference for parameter estimation in ATLAS",
abstract = "Neural simulation-based inference (NSBI) is a powerful class of machine-learning-based methods for statistical inference that naturally handles high-dimensional parameter estimation without the need to bin data into low-dimensional summary histograms. Such methods are promising for a range of measurements, including at the Large Hadron Collider, where no single observable may be optimal to scan over the entire theoretical phase space under consideration, or where binning data into histograms could result in a loss of sensitivity. This work develops a NSBI framework for statistical inference, using neural networks to estimate probability density ratios, which enables the application to a full-scale analysis. It incorporates a large number of systematic uncertainties, quantifies the uncertainty due to the finite number of events in training samples, develops a method to construct confidence intervals, and demonstrates a series of intermediate diagnostic checks that can be performed to validate the robustness of the method. As an example, the power and feasibility of the method are assessed on simulated data for a simplified version of an off-shell Higgs boson couplings measurement in the four-lepton final states. This approach represents an extension to the standard statistical methodology used by the experiments at the Large Hadron Collider, and can benefit many physics analyses.",
author = "{The ATLAS collaboration} and Hanadi Ali and Zainab Alsolami and A.E. Barton and G. Borissov and E.V. Bouhova-Thacker and Ruby Ferguson and James Ferrando and H. Fox and Alina Hagan and R.C.W. Henderson and R.W.L. Jones and V. Kartvelishvili and P.A. Love and Marshall, {Emma J.} and Luke McElhinney and L. Meng and D. Muenstermann and Elliot Sampson and M. Smizanska and A.M. Wharton",
year = "2025",
month = may,
day = "27",
doi = "10.1088/1361-6633/add370",
language = "English",
volume = "88",
journal = "Reports on Progress in Physics",
issn = "0034-4885",
publisher = "IOP Publishing Ltd.",
number = "6",

}

RIS

TY - JOUR

T1 - An implementation of neural simulation-based inference for parameter estimation in ATLAS

AU - The ATLAS collaboration

AU - Ali, Hanadi

AU - Alsolami, Zainab

AU - Barton, A.E.

AU - Borissov, G.

AU - Bouhova-Thacker, E.V.

AU - Ferguson, Ruby

AU - Ferrando, James

AU - Fox, H.

AU - Hagan, Alina

AU - Henderson, R.C.W.

AU - Jones, R.W.L.

AU - Kartvelishvili, V.

AU - Love, P.A.

AU - Marshall, Emma J.

AU - McElhinney, Luke

AU - Meng, L.

AU - Muenstermann, D.

AU - Sampson, Elliot

AU - Smizanska, M.

AU - Wharton, A.M.

PY - 2025/5/27

Y1 - 2025/5/27

N2 - Neural simulation-based inference (NSBI) is a powerful class of machine-learning-based methods for statistical inference that naturally handles high-dimensional parameter estimation without the need to bin data into low-dimensional summary histograms. Such methods are promising for a range of measurements, including at the Large Hadron Collider, where no single observable may be optimal to scan over the entire theoretical phase space under consideration, or where binning data into histograms could result in a loss of sensitivity. This work develops a NSBI framework for statistical inference, using neural networks to estimate probability density ratios, which enables the application to a full-scale analysis. It incorporates a large number of systematic uncertainties, quantifies the uncertainty due to the finite number of events in training samples, develops a method to construct confidence intervals, and demonstrates a series of intermediate diagnostic checks that can be performed to validate the robustness of the method. As an example, the power and feasibility of the method are assessed on simulated data for a simplified version of an off-shell Higgs boson couplings measurement in the four-lepton final states. This approach represents an extension to the standard statistical methodology used by the experiments at the Large Hadron Collider, and can benefit many physics analyses.

AB - Neural simulation-based inference (NSBI) is a powerful class of machine-learning-based methods for statistical inference that naturally handles high-dimensional parameter estimation without the need to bin data into low-dimensional summary histograms. Such methods are promising for a range of measurements, including at the Large Hadron Collider, where no single observable may be optimal to scan over the entire theoretical phase space under consideration, or where binning data into histograms could result in a loss of sensitivity. This work develops a NSBI framework for statistical inference, using neural networks to estimate probability density ratios, which enables the application to a full-scale analysis. It incorporates a large number of systematic uncertainties, quantifies the uncertainty due to the finite number of events in training samples, develops a method to construct confidence intervals, and demonstrates a series of intermediate diagnostic checks that can be performed to validate the robustness of the method. As an example, the power and feasibility of the method are assessed on simulated data for a simplified version of an off-shell Higgs boson couplings measurement in the four-lepton final states. This approach represents an extension to the standard statistical methodology used by the experiments at the Large Hadron Collider, and can benefit many physics analyses.

U2 - 10.1088/1361-6633/add370

DO - 10.1088/1361-6633/add370

M3 - Journal article

VL - 88

JO - Reports on Progress in Physics

JF - Reports on Progress in Physics

SN - 0034-4885

IS - 6

M1 - 067801

ER -