Holographic Renormalization with Machine learning

TL;DR

This paper introduces a deep learning approach inspired by the Renormalization Group to identify relevant degrees of freedom and induce scale invariance, providing insights into holographic entanglement entropy and the AdS/CFT correspondence.

Contribution

It develops a neural network-based method that mimics RG schemes to discover physical degrees of freedom and explore holographic principles without prior system knowledge.

Findings

Deep learning can identify relevant degrees of freedom in physical systems.

The method induces scale invariance through an RG-like neural network scheme.

Insights into holographic entanglement entropy and AdS/CFT are gained.

Abstract

At low energies, the microscopic characteristics and changes of physical systems as viewed at different distance scales are described by universal scale invariant properties investigated by the Renormalization Group (RG) apparatus, an efficient tool used to deal with scaling problems in effective field theories. We employ an information-theoretic approach in a deep learning setup by introducing an artificial neural network algorithm to map and identify new physical degrees of freedom. Using deep learning methods mapped to a genuine field theory, we develop a mechanism capable to identify relevant degrees of freedom and induce scale invariance without prior knowledge about a system. We show that deep learning algorithms that use an RG-like scheme to learn relevant features from data could help to understand the nature of the holographic entanglement entropy and the holographic principle in context of the AdS/CFT correspondence.