Decoding the proton's gluonic density with lattice QCD-informed machine learning

TL;DR

This paper introduces a machine learning approach using a variational autoencoder to decode the gluonic structure of the proton from lattice QCD data, achieving results consistent with global fits and demonstrating the potential of AI to connect theoretical and experimental insights.

Contribution

It presents the first application of a generative AI model, VAIM, to extract the gluon parton distribution function from lattice QCD data, bridging a gap between theory and phenomenology.

Findings

Gluon PDF predictions align with global fits within uncertainties.

VAIM learns a meaningful latent representation of lattice QCD data.

The approach effectively constrains the gluon distribution in the proton.

Abstract

We present a first machine learning-based decoding of the gluonic structure of the proton from lattice QCD using a variational autoencoder inverse mapper (VAIM). Harnessing the power of generative AI, we predict the parton distribution function (PDF) of the gluon given information on the reduced pseudo-Ioffe-time distributions (RpITDs) as calculated from an ensemble with lattice spacing $a\! \approx\! 0.09$ fm and a pion mass of $M_\pi\! \approx\! 310$ MeV. The resulting gluon PDF is consistent with phenomenological global fits within uncertainties, particularly in the intermediate-to-high-$x$ region where lattice data are most constraining. A subsequent correlation analysis confirms that the VAIM learns a meaningful latent representation, highlighting the potential of generative AI to bridge lattice QCD and phenomenological extractions within a unified analysis framework.