Speaker
Suprio Dubey
(Heidelberg University)
Description
Neural network surrogates for LHC scattering amplitudes require trustworthy uncertainty estimates, a challenging task given the non-Gaussian systematics. We target it
using conformal prediction, a distribution-free post-processing to complement trained
surrogates with calibrated uncertainties. We find that standard conformal predictions
struggle to provide locally calibrated uncertainties. This leads us to introduce FALCON,
a novel conformal prediction method that learns locally calibrated confidence intervals.
Our simple examples illustrate the power of distribution-free uncertainty quantification
for ultra-fast event generation at the LHC.
Authors
Anja Butter
(Centre National de la Recherche Scientifique (FR))
Henning Bahl
Prof.
Jürgen Hesser
(Mannheim Institute for Intelligent Systems in Medicine, Interdisciplinary Center for Scientific Computing (IWR), Central Institute for Computer Engineering (ZITI),CZS Heidelberg Initiative for Model-Based AI (MBAI), Universität Heidelberg, Germany)
Suprio Dubey
(Heidelberg University)
Tilman Plehn