Autoregressive neural quantum states of Fermi Hubbard models

TL;DR

This paper explores the application of autoregressive neural networks, specifically RNNs and transformers, to simulate Fermi-Hubbard models, addressing convergence challenges and proposing strategies to improve optimization in strongly-correlated electron systems.

Contribution

It introduces a ramping strategy for better optimization of neural quantum states and analyzes the effects of autoregressive sampling in non-Hermitian models.

Findings

RNN ansatz convergence is challenged at higher interaction strengths.

Ramping model parameters improves optimization.

Autoregressive sampling poses challenges in non-Hermitian models.

Abstract

Neural quantum states (NQS) have emerged as a powerful ansatz for variational quantum Monte Carlo studies of strongly-correlated systems. Here, we apply recurrent neural networks (RNNs) and autoregressive transformer neural networks to the Fermi-Hubbard and the (non-Hermitian) Hatano-Nelson-Hubbard models in one and two dimensions. In both cases, we observe that the convergence of the RNN ansatz is challenged when increasing the interaction strength. We present a physically-motivated and easy-to-implement strategy for improving the optimization, namely, by ramping of the model parameters. Furthermore, we investigate the advantages and disadvantages of the autoregressive sampling property of both network architectures. For the Hatano-Nelson-Hubbard model, we identify convergence issues that stem from the autoregressive sampling scheme in combination with the non-Hermitian nature of the model. Our findings provide insights into the challenges of the NQS approach and make the first step towards exploring strongly-correlated electrons using this ansatz.