arXiv · 2607.25282
Normalizing Flows to Reconstruct Pseudo-PDFs
Abstract
We investigate a normalizing-flow approach for reconstructing parton distribution functions (PDFs) from synthetic matrix-element data. Our framework combines Gaussian Process priors with invertible neural networks to learn a posterior distribution over PDFs consistent with limited Ioffe-time data. We demonstrate that the architecture preserves physical constraints and extrapolation properties.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yamil Cahuana Medrano, Kostas Orginos. 2026-07-28. Normalizing Flows to Reconstruct Pseudo-PDFs. https://arxiv.org/abs/2607.25282
Cite the original work for its findings. Save a collection to share your selection of sources.