Data Repository for: Machine-learning the spectral function of a hole in a quantum antiferromagnet

The machine-learning dataset of 51^3 ~1.3 × 10^5 density of states (DOS) of a mobile hole in the t-t'-t''-J model theoretically generated by using the self-consistent Born approximation in the three-dimensional parameter space of t′ ∈ [−0.5, 0.5], t′′ ∈ [−0.5, 0.5] and J ∈ [0.2, 1.0], with each parameter sampled on a 51-point uniform grid. The dataset is randomly partitioned into an 80/10/10 training (T), validation (V), and testing T split. Note that each DOS A(ω) was calculated on a 1201-point uniform grid of ω ∈ [−6t, 6t], then it was resampled on a 301-point uniform grid for the forward problem and on a 354-point uniform grid for the inverse problem. The dataset used in the inverse problem is limited to the parameter space of  t′ ∈ [−0.5, 0], t′′ ∈ [0, 0.5] and J ∈ [0.2, 1.0].  To open the enclosed .npz files, use numpy.load() in python3.