Fidelity and Overlap of Neural Quantum States: Error Bounds on the Monte Carlo Estimator

Abstract

Overlap between two neural quantum states can be computed through Monte Carlo sampling by evaluating the unnormalized probability amplitudes on a subset of basis configurations. Due to the presence of probability amplitude ratios in the estimator, which are possibly unbounded, convergence of this quantity is not immediately obvious. Our work provides a derivation of analytical error bounds on the overlap in the Monte Carlo calculations as a function of their fidelity and the number of samples. Special case of normalized autoregressive neural quantum states is analyzed separately.