Learning of Statistical Field Theories

TL;DR

This paper introduces a versatile method for inferring microscopic couplings in statistical field theories from data, enabling analysis of complex systems and non-perturbative phenomena without relying on traditional perturbative approaches.

Contribution

The authors develop a unified inverse learning approach applicable to systems with discrete, continuous, and hybrid variables, demonstrating accurate parameter recovery and non-perturbative renormalization group flow reconstruction.

Findings

Accurate parameter recovery in benchmark models like Ising gauge and $\

4 theory, Schwinger, and Sine-Gordon models.

Reconstruction of non-perturbative RG flows and phase boundaries from data.

Abstract

Recovering microscopic couplings directly from data provides a route to solving the inverse problem in statistical field theories, one that complements the traditional-often computationally intractable-forward approach of predicting observables from an action or Hamiltonian. Here, we propose an approach for the inverse problem that uniformly accommodates systems with discrete, continuous, and hybrid variables. We demonstrate accurate parameter recovery in several benchmark systems-including Wegner's Ising gauge theory, $\phi^4$ theory, Schwinger and Sine-Gordon models, and mixed spin-gauge systems, and show how iterating the procedure under coarse-graining reconstructs full non-perturbative renormalization-group flows. This gives direct access to phase boundaries, fixed points, and emergent interactions without relying on perturbation theory. We also address a realistic setting where full gauge configurations may be unavailable, and reformulate learning algorithms for multiple field theories so that they are recovered directly using observables such as correlations from scattering data or quantum simulators. We anticipate that our methodology will find widespread use in practical learning of field theories in strongly coupled regimes where analytical tools might fail.