Learning a compass spin model with neural network quantum states

TL;DR

This paper demonstrates that neural network quantum states, specifically restricted Boltzmann machines, can effectively model complex magnetic orders and phase diagrams in frustrated quantum spin systems like the compass model.

Contribution

It shows the successful application of RBMs to describe ground states and phase diagrams of a complex compass spin model, highlighting their potential in frustrated quantum magnetism.

Findings

RBMs accurately approximate ground states of the compass model

Phase diagram aligns with tensor network predictions

Discusses limitations and strategies for improving machine learning in quantum magnets

Abstract

Neural network quantum states provide a novel representation of the many-body states of interacting quantum systems and open up a promising route to solve frustrated quantum spin models that evade other numerical approaches. Yet its capacity to describe complex magnetic orders with large unit cells has not been demonstrated, and its performance in a rugged energy landscape has been questioned. Here we apply restricted Boltzmann machines and stochastic gradient descent to seek the ground states of a compass spin model on the honeycomb lattice, which unifies the Kitaev model, Ising model and the quantum 120$^\circ$ model with a single tuning parameter. We report calculation results on the variational energy, order parameters and correlation functions. The phase diagram obtained is in good agreement with the predictions of tensor network ansatz, demonstrating the capacity of restricted Boltzmann machines in learning the ground states of frustrated quantum spin Hamiltonians. The limitations of the calculation are discussed. A few strategies are outlined to address some of the challenges in machine learning frustrated quantum magnets.