Interpretable Quantum Advantage in Neural Sequence Learning

TL;DR

This paper demonstrates that quantum neural networks possess an inherent advantage in sequence learning due to quantum contextuality, outperforming classical models on linguistic tasks.

Contribution

It identifies quantum contextuality as the source of quantum advantage in neural sequence models and shows practical performance improvements.

Findings

Quantum contextuality causes a memory separation in expressivity.

Quantum models outperform classical models on linguistic datasets.

The study provides intuition linking quantum properties to practical advantages.

Abstract

Quantum neural networks have been widely studied in recent years, given their potential practical utility and recent results regarding their ability to efficiently express certain classical data. However, analytic results to date rely on assumptions and arguments from complexity theory. Due to this, there is little intuition as to the source of the expressive power of quantum neural networks or for which classes of classical data any advantage can be reasonably expected to hold. Here, we study the relative expressive power between a broad class of neural network sequence models and a class of recurrent models based on Gaussian operations with non-Gaussian measurements. We explicitly show that quantum contextuality is the source of an unconditional memory separation in the expressivity of the two model classes. Additionally, as we are able to pinpoint quantum contextuality as the source of this separation, we use this intuition to study the relative performance of our introduced model on a standard translation data set exhibiting linguistic contextuality. In doing so, we demonstrate that our introduced quantum models are able to outperform state of the art classical models even in practice.