Provable superior accuracy in machine learned quantum models

TL;DR

This paper introduces machine learning methods to construct quantum models that are dimensionally reduced yet more accurate than classical models, demonstrating a provable quantum advantage on current hardware for time-series prediction.

Contribution

The authors develop a novel algorithm for creating dimensionally reduced quantum models that outperform classical models in accuracy, with provable quantum advantage demonstrated on real hardware.

Findings

Quantum models achieve greater accuracy than classical counterparts.

The method is applicable directly to classical time-series data.

Quantum advantage is provably established in this context.

Abstract

In modelling complex processes, the potential past data that influence future expectations are immense. Models that track all this data are not only computationally wasteful but also shed little light on what past data most influence the future. There is thus enormous interest in dimensional reduction-finding automated means to reduce the memory dimension of our models while minimizing its impact on its predictive accuracy. Here we construct dimensionally reduced quantum models by machine learning methods that can achieve greater accuracy than provably optimal classical counterparts. We demonstrate this advantage on present-day quantum computing hardware. Our algorithm works directly off classical time-series data and can thus be deployed in real-world settings. These techniques illustrate the immediate relevance of quantum technologies to time-series analysis and offer a rare instance where the resulting quantum advantage can be provably established.