DOE OSTI · 2007976
MadNIS - Neural multi-channel importance sampling
Abstract
Theory predictions for the LHC require precise numerical phase-space integration and generation of unweighted events. We combine machine-learned multi-channel weights with a normalizing flow for importance sampling, to improve classical methods for numerical integration. We develop an efficient bi-directional setup based on an invertible network, combining online and buffered training for potentially expensive integrands. We illustrate our method for the Drell-Yan process with an additional narrow resonance.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Heimel, Theo, Winterhalder, Ramon, Butter, Anja, Isaacson, Joshua, Krause, Claudius, Maltoni, Fabio, Mattelaer, Olivier, Plehn, Tilman. 2023-10-06. MadNIS - Neural multi-channel importance sampling. https://doi.org/10.21468/scipostphys.15.4.141
Cite the original work for its findings. Save a collection to share your selection of sources.