Variational autoencoder inverse mapper for extraction of Compton form factors: Benchmarks and conditional learning

TL;DR

This paper introduces a variational autoencoder-based method for extracting Compton form factors from DVCS data, demonstrating consistency with traditional methods and capturing correlations among factors for improved GPD analysis.

Contribution

It presents a novel variational autoencoder inverse mapper approach for CFF extraction, including a constrained variant that captures correlations across kinematics, advancing GPD analysis.

Findings

VAIM matches MCMC in CFF extraction accuracy

C-VAIM captures CFF correlations across kinematics

Method advances the GPD extraction pipeline

Abstract

Deeply virtual exclusive scattering processes (DVES) serve as precise probes of nucleon quark and gluon distributions in coordinate space. These distributions are derived from generalized parton distributions (GPDs) via Fourier transform relative to proton momentum transfer. QCD factorization theorems enable DVES to be parameterized by Compton form factors (CFFs), which are convolutions of GPDs with perturbatively calculable kernels. Accurate extraction of CFFs from DVCS, benefiting from interference with the Bethe-Heitler (BH) process and a simpler final state structure, is essential for inferring GPDs. This paper focuses on extracting CFFs from DVCS data using a variational autoencoder inverse mapper (VAIM) and its constrained variant (C-VAIM). VAIM is shown to be consistent with Markov Chain Monte Carlo (MCMC) methods in extracting multiple CFF solutions for given kinematics, while C-VAIM effectively captures correlations among CFFs across different kinematic values, providing more constrained solutions. This study represents a crucial first step towards a comprehensive analysis pipeline towards the extraction of GPDs.