Entanglement-induced provable and robust quantum learning advantages

TL;DR

This paper establishes a noise-robust, provable quantum learning advantage over classical models in expressivity, inference speed, and training efficiency, leveraging entanglement to solve non-local tasks more efficiently.

Contribution

It provides the first rigorous proof of a noise-robust quantum learning advantage based on entanglement, with experimental validation on IonQ Aria.

Findings

Quantum models solve certain tasks with constant parameters using entanglement.

Classical models require linear scaling to achieve similar accuracy.

Experimental results confirm the theoretical advantage.

Abstract

Quantum computing holds unparalleled potentials to enhance machine learning. However, a demonstration of quantum learning advantage has not been achieved so far. We make a step forward by rigorously establishing a noise-robust, unconditional quantum learning advantage in expressivity, inference speed, and training efficiency, compared to commonly-used classical models. Our proof is information-theoretic and pinpoints the origin of this advantage: entanglement can be used to reduce the communication required by non-local tasks. In particular, we design a task that can be solved with certainty by quantum models with a constant number of parameters using entanglement, whereas commonly-used classical models must scale linearly to achieve a larger-than-exponentially-small accuracy. We show that the quantum model is trainable with constant resources and robust against constant noise. Through numerical and trapped-ion experiments on IonQ Aria, we demonstrate the desired advantage. Our results provide valuable guidance for demonstrating quantum learning advantages with current noisy intermediate-scale devices.