Amplitude uncertainties everywhere all at once, by Henning Bahl, Nina Elmer, Tilman Plehn, Ramon Winterhalder

SciPost Physics Home Authoring Refereeing Submit a manuscript About Amplitude uncertainties everywhere all at once Henning Bahl, Nina Elmer, Tilman Plehn, Ramon Winterhalder SciPost Phys. 20, 083 (2026) · published 12 March 2026 doi: 10.21468/SciPostPhys.20.3.083 pdf BiBTeX RIS Submissions/Reports Abstract Ultra-fast, precise, and controlled amplitude surrogates are essential for future LHC event generation. First, we investigate the noise reduction and biases of network ensembles and outline a new method to learn well-calibrated systematic uncertainties for them. We also establish evidential regression as a sampling-free method for uncertainty quantification. In a second part, we tackle localized disturbances for amplitude regression and demonstrate that learned uncertainties from Bayesian networks, ensembles, and evidential regression all identify numerical noise or gaps in the training data. × TY - JOURPB - SciPost FoundationDO - 10.21468/SciPostPhys.20.3.083TI - Amplitude uncertainties everywhere all at oncePY - 2026/03/12UR - https://scipost.org/SciPostPhys.20.3.083JF - SciPost PhysicsJA - SciPost Phys.VL - 20IS - 3SP - 083A1 - Bahl, HenningAU - Elmer, NinaAU - Plehn, TilmanAU - Winterhalder, RamonAB - Ultra-fast, precise, and controlled amplitude surrogates are essential for future LHC event generation. First, we investigate the noise reduction and biases of network ensembles and outline a new method to learn well-calibrated systematic uncertainties for them. We also establish evidential regression as a sampling-free method for uncertainty quantification. In a second part, we tackle localized disturbances for amplitude regression and demonstrate that learned uncertainties from Bayesian networks, ensembles, and evidential regression all identify numerical noise or gaps in the training data.ER - × @Article{10.21468/SciPostPhys.20.3.083, title={{Amplitude uncertainties everywhere all at once}}, author={Henning Bahl and Nina Elmer and Tilman Plehn and Ramon Winterhalder}, journal={SciPost Phys.}, volume={20}, pages={083}, year={2026}, publisher={SciPost}, doi={10.21468/SciPostPhys.20.3.083}, url={https://scipost.org/10.21468/SciPostPhys.20.3.083},} Ontology / Topics See full Ontology or Topics database. Machine learning (ML) Monte-Carlo simulations Authors / Affiliations: mappings to Contributors and Organizations See all Organizations. 1 Henning Bahl, 1 Nina Elmer, 1 Tilman Plehn, 2 3 Ramon Winterhalder 1 Ruprecht-Karls-Universität Heidelberg / Heidelberg University 2 Università degli Studi di Milano / University of Milan [UNIMI] 3 Istituto Nazionale di Fisica Nucleare Sezione di Milano / INFN Sezione di Milano Funders for the research work leading to this publication Baden-Württemberg Stiftung Bundesministerium für Bildung und Forschung / Federal Ministry of Education and Research [BMBF] Deutsche Forschungsgemeinschaft / German Research FoundationDeutsche Forschungsgemeinschaft [DFG]