Learning quantum states and unitaries of bounded gate complexity

TL;DR

This paper investigates the fundamental limits of efficiently learning quantum states and unitaries generated by circuits with bounded gate complexity, establishing linear sample complexity and exponential computational hardness under cryptographic assumptions.

Contribution

It proves that learning such quantum states and unitaries requires sample complexity linear in gate count and shows computational hardness assuming cryptographic conjectures.

Findings

Sample complexity scales linearly with the number of gates G.

Optimal query complexity for unitaries also scales linearly with G.

Computational hardness of learning scales exponentially with G under cryptographic assumptions.

Abstract

While quantum state tomography is notoriously hard, most states hold little interest to practically-minded tomographers. Given that states and unitaries appearing in Nature are of bounded gate complexity, it is natural to ask if efficient learning becomes possible. In this work, we prove that to learn a state generated by a quantum circuit with $G$ two-qubit gates to a small trace distance, a sample complexity scaling linearly in $G$ is necessary and sufficient. We also prove that the optimal query complexity to learn a unitary generated by $G$ gates to a small average-case error scales linearly in $G$. While sample-efficient learning can be achieved, we show that under reasonable cryptographic conjectures, the computational complexity for learning states and unitaries of gate complexity $G$ must scale exponentially in $G$. We illustrate how these results establish fundamental limitations on the expressivity of quantum machine learning models and provide new perspectives on no-free-lunch theorems in unitary learning. Together, our results answer how the complexity of learning quantum states and unitaries relate to the complexity of creating these states and unitaries.