We present the first proof of principle that normalizing flows can accurately learn the Boltzmann distribution of the fermionic Hubbard model - a key framework for describing the electronic structure of graphene and related materials. State-of-the-art methods like Hybrid Monte Carlo often suffer from ergodicity issues near the time-continuum limit, leading to biased estimates. Leveraging symmetry-aware architectures as well as independent and identically distributed sampling, our approach resolves these issues and achieves significant speed-ups over traditional methods.
@article{arxiv.2506.17015,
title = {Simulating Correlated Electrons with Symmetry-Enforced Normalizing Flows},
author = {Dominic Schuh and Janik Kreit and Evan Berkowitz and Lena Funcke and Thomas Luu and Kim A. Nicoli and Marcel Rodekamp},
journal= {arXiv preprint arXiv:2506.17015},
year = {2025}
}