Machine Learning Applications for Holographic QCD

Recent progress on the application of machine learning in holographic QCD will be presented. Within the holographic framework, the extra radial dimension of the bulk spacetime geometrically encodes the renormalization group scale of the boundary quantum field theory. Inspired by the structural similarity between holography and deep neural networks, machine learning provides new tools to study strongly coupled QCD in a data-driven way.

Several applications will be discussed, including parameter optimization in holographic models, uncertainty quantification through Bayesian inference, solving inverse problems by reconstructing bulk dynamics from QCD observables, and discovering analytical relations using symbolic regression. These developments demonstrate that machine learning can significantly improve the predictive power and flexibility of holographic QCD models and may provide new insights into strongly coupled quantum field theories.

Speaker: Xun Chen (Assegnista INFN Bari)

When: 13 March 2026 at 10:30

Where: Aula Multimediale (Dipartimento di Fisica)