HoloNet: Toward a Unified Einstein-Maxwell-Dilaton Framework of QCD

TL;DR

HoloNet is a neural network framework that learns from lattice QCD data to create a unified holographic model of QCD, accurately capturing thermodynamics and phase transitions.

Contribution

HoloNet introduces a data-driven approach to learn holographic functions directly from lattice QCD data, enabling a consistent and extendable QCD holographic description.

Findings

Successfully reproduces lattice QCD thermodynamics and fluctuations.

Maps the QCD phase diagram and estimates the critical end point.

Reconstructs holographic potentials consistent with known models.

Abstract

We propose HoloNet, a neural-network framework that unifies lattice QCD(LQCD) thermodynamics and holographic Einstein-Maxwell-Dilaton (EMD) theory within a data-to-holography pipeline. Instead of assuming specific functional forms, HoloNet learns the metric profile $A(z)$ and the gauge-dilaton coupling $f(z)$ directly from 2+1-flavor LQCD data at $\mu=0$. These learned functions are embedded into the EMD equations, enabling the model to reproduce the lattice equation of state and baryon number fluctuations with high fidelity. Once trained, HoloNet provides a fully data-driven holographic description of QCD that extends naturally to finite density, allowing us to map the phase diagram and estimate the location of the critical end point (CEP). The reconstructed potential $V(\phi)$ and coupling $f(\phi)$ agree quantitatively with those obtained from holographic renormalization, demonstrating that HoloNet can consistently bridge different holographic models.