A scalable advantage in multi-photon quantum machine learning

TL;DR

This paper demonstrates both theoretically and experimentally that multi-photon quantum states in photonic circuits can provide scalable advantages in machine learning tasks, showing polynomial scaling of learning capacity and successful experimental validation.

Contribution

It establishes a theoretical foundation and experimental proof for scalable quantum advantage in photonic quantum machine learning using multi-photon states.

Findings

Learning capacity scales polynomially with photon number.

Experimental validation on unitary and metric learning tasks.

Photonic platform enables practical quantum machine learning improvements.

Abstract

Photons are promising candidates for quantum information technology due to their high robustness and long coherence time at room temperature. Inspired by the prosperous development of photonic computing techniques, recent research has turned attention to performing quantum machine learning on photonic platforms. Although photons possess a high-dimensional quantum feature space suitable for computation, a general understanding of how to harness it for learning tasks remains blank. Here, we establish both theoretically and experimentally a scalable advantage in quantum machine learning with multi-photon states. Firstly, we prove that the learning capacity of linear optical circuits scales polynomially with the photon number, enabling generalization from smaller training datasets and yielding lower test loss values. Moreover, we experimentally corroborate these findings through unitary learning and metric learning tasks, by performing online training on a fully programmable photonic integrated platform. Our work highlights the potential of photonic quantum machine learning and paves the way for achieving quantum enhancement in practical machine learning applications.