Fig. 2: Predicting ground state properties in 2D antiferromagnetic random Heisenberg models.
From: Improved machine learning algorithm for predicting ground state properties
a Prediction error. Each point indicates the root-mean-square error for predicting the correlation function in the ground state (averaged over Heisenberg model instances and each pair of neighboring spins). We present log-log plots for the scaling of prediction error ϵ with T and N: the slope corresponds to the exponent of the polynomial function ϵ(T), ϵ(N). The shaded regions show the standard deviation over different spin pairs. b Visualization. We plot how much each coupling Jij contributes to the prediction of the correlation function over different pairs of qubits in the trained ML model. Thicker and darker edges correspond to higher contributions. We see that the ML model learns to utilize the local geometric structure.
