Dr. Henning Bahl

Neural networks for LHC physics have to be accurate, reliable, and controlled. Using surrogate loop amplitudes as a use case, I will first show how activation functions can be systematically tested with KANs. For reliability and control, I will demonstrate how to learn uncertainties together with the target amplitude over phase space. Systematic uncertainties can be learned by a heteroscedastic loss, but a comprehensive learned uncertainty requires Bayesian networks or repulsive ensembles. I will also discuss pull distributions which quantify to what level learned uncertainties are calibrated correctly for cutting-edge precision surrogates.