Accurate surrogate amplitudes with calibrated uncertainties

Favaro, Luigi;et.al.
(2025) SciPost Physics Core — Vol. 8 (2025)

Files

document.pdf
  • Open Access
  • Adobe PDF
  • 552.74 KB
Download

Details

Authors
Abstract
Neural networks for LHC physics have to be accurate, reliable, and controlled. Using neural surrogates for the prediction of loop amplitudes as a use case, we first show how activation functions are systematically tested with Kolmogorov-Arnold Networks. Then, we train neural surrogates to simultaneously predict the target amplitude and an uncertainty for the prediction. We disentangle systematic uncertainties, learned by a well-defined likelihood loss, from statistical uncertainties, which require the introduction of Bayesian neural networks or repulsive ensembles. We test the coverage of the learned uncertainties using pull distributions to quantify the calibration of cutting-edge neural surrogates.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Favaro, L., & et al. (2025). Accurate surrogate amplitudes with calibrated uncertainties. SciPost Physics Core, 8. https://doi.org/10.21468/SciPostPhysCore.8.4.073 (Original work published 2025)