Classification of the Fashion-MNIST Dataset on a Quantum Computer

TL;DR

This paper presents an improved quantum data encoding algorithm applied to the Fashion-MNIST dataset, demonstrating its feasibility on current quantum hardware with moderate classification accuracy, advancing near-term quantum machine learning research.

Contribution

It introduces a shallow, hardware-efficient variational encoding algorithm for classical data, enabling practical quantum machine learning experiments on current devices.

Findings

Successfully encoded Fashion-MNIST on a quantum computer

Achieved moderate classification accuracy with quantum variational classifiers

Provided a proof of concept for near-term quantum data encoding methods

Abstract

The potential impact of quantum machine learning algorithms on industrial applications remains an exciting open question. Conventional methods for encoding classical data into quantum computers are not only too costly for a potential quantum advantage in the algorithms but also severely limit the scale of feasible experiments on current hardware. Therefore, recent works, despite claiming the near-term suitability of their algorithms, do not provide experimental benchmarking on standard machine learning datasets. We attempt to solve the data encoding problem by improving a recently proposed variational algorithm [1] that approximately prepares the encoded data, using asymptotically shallow circuits that fit the native gate set and topology of currently available quantum computers. We apply the improved algorithm to encode the Fashion-MNIST dataset [2], which can be directly used in future empirical studies of quantum machine learning algorithms. We deploy simple quantum variational classifiers trained on the encoded dataset on a current quantum computer ibmq-kolkata [3] and achieve moderate accuracies, providing a proof of concept for the near-term usability of our data encoding method.