Performance Guarantees for Quantum Neural Estimation of Entropies

TL;DR

This paper provides theoretical error bounds and concentration results for quantum neural estimators used to measure quantum entropies, aiding their practical implementation.

Contribution

It establishes non-asymptotic error guarantees and tail bounds for QNEs, including optimal sample complexity and improved bounds for permutation-invariant cases.

Findings

Error risk bounds for quantum neural estimators of measured relative entropies.

Exponential tail bounds showing sub-Gaussian concentration of estimation error.

Sample complexity bounds with minimax optimal dependence on accuracy and improved bounds for permutation-invariant states.

Abstract

Estimating quantum entropies and divergences is an important problem in quantum physics, information theory, and machine learning. Quantum neural estimators (QNEs), which utilize a hybrid classical-quantum architecture, have recently emerged as an appealing computational framework for estimating these measures. Such estimators combine classical neural networks with parametrized quantum circuits, and their deployment typically entails tedious tuning of hyperparameters controlling the sample size, network architecture, and circuit topology. This work initiates the study of formal guarantees for QNEs of measured (R\'enyi) relative entropies in the form of non-asymptotic error risk bounds. We further establish exponential tail bounds showing that the error is sub-Gaussian and thus sharply concentrates about the ground truth value. For an appropriate sub-class of density operator pairs on a space of dimension $d$ with bounded Thompson metric, our theory establishes a copy complexity of $O(|\Theta(\mathcal{U})|d/\epsilon^2)$ for QNE with a quantum circuit parameter set $\Theta(\mathcal{U})$, which has minimax optimal dependence on the accuracy $\epsilon$. Additionally, if the density operator pairs are permutation invariant, we improve the dimension dependence above to $O(|\Theta(\mathcal{U})|\mathrm{polylog}(d)/\epsilon^2)$. Our theory aims to facilitate principled implementation of QNEs for measured relative entropies and guide hyperparameter tuning in practice.