Deep Learning the Functional Renormalization Group
Abstract
We perform a data-driven dimensionality reduction of the scale-dependent 4-point vertex function characterizing the functional Renormalization Group (fRG) flow for the widely studied two-dimensional Hubbard model on the square lattice. We demonstrate that a deep learning architecture based on a Neural Ordinary Differential Equation solver in a low-dimensional latent space efficiently learns the fRG dynamics that delineates the various magnetic and -wave superconducting regimes of the Hubbard model. We further present a Dynamic Mode Decomposition analysis that confirms that a small number of modes are indeed sufficient to capture the fRG dynamics. Our work demonstrates the possibility of using artificial intelligence to extract compact representations of the 4-point vertex functions for correlated electrons, a goal of utmost importance for the success of cutting-edge quantum field theoretical methods for tackling the many-electron problem.
Cite
@article{arxiv.2202.13268,
title = {Deep Learning the Functional Renormalization Group},
author = {Domenico Di Sante and Matija Medvidović and Alessandro Toschi and Giorgio Sangiovanni and Cesare Franchini and Anirvan M. Sengupta and Andrew J. Millis},
journal= {arXiv preprint arXiv:2202.13268},
year = {2023}
}
Comments
6 pages, 5 figures