Experimental data re-uploading with provable enhanced learning capabilities

TL;DR

This paper demonstrates a photonic quantum machine learning model using data re-uploading, achieving high accuracy and universality, with theoretical proof of its generalization capabilities, paving the way for resource-efficient quantum algorithms.

Contribution

It provides the first experimental implementation of data re-uploading on a photonic processor with proven universality and generalization, along with theoretical insights into its capabilities.

Findings

Achieved high accuracy in image classification tasks.

Proved the model's universality as a classifier.

Demonstrated effective generalization to new data.

Abstract

The last decades have seen the development of quantum machine learning, stemming from the intersection of quantum computing and machine learning. This field is particularly promising for the design of alternative quantum (or quantum inspired) computation paradigms that could require fewer resources with respect to standard ones, e.g. in terms of energy consumption. In this context, we present the implementation of a data re-uploading scheme on a photonic integrated processor, achieving high accuracies in several image classification tasks. We thoroughly investigate the capabilities of this apparently simple model, which relies on the evolution of one-qubit states, by providing an analytical proof that our implementation is a universal classifier and an effective learner, capable of generalizing to new, unknown data. Hence, our results not only demonstrate data re-uploading in a potentially resource-efficient optical implementation but also provide new theoretical insight into this algorithm, its trainability, and generalizability properties. This lays the groundwork for developing more resource-efficient machine learning algorithms, leveraging our scheme as a subroutine.