Normalizing Flows to Reconstruct Pseudo-PDFs

arXiv:2607.25282v1 Announce Type: cross 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.

Source: arXiv cs.LG | 2026-07-29