QUILT: Effective Multi-Class Classification on Quantum Computers Using an Ensemble of Diverse Quantum Classifiers

TL;DR

QUILT is a framework that enables effective multi-class classification on current noisy quantum computers by using an ensemble of diverse quantum classifiers, achieving high accuracy on real hardware.

Contribution

It introduces a novel ensemble-based framework tailored for noisy intermediate-scale quantum computers to perform multi-class classification effectively.

Findings

Achieves up to 85% accuracy on MNIST with five qubits.

Demonstrates robustness across real and simulated noise levels.

Shows potential for near-term quantum machine learning applications.

Abstract

Quantum computers can theoretically have significant acceleration over classical computers; but, the near-future era of quantum computing is limited due to small number of qubits that are also error prone. Quilt is a framework for performing multi-class classification task designed to work effectively on current error-prone quantum computers. Quilt is evaluated with real quantum machines as well as with projected noise levels as quantum machines become more noise-free. Quilt demonstrates up to 85% multi-class classification accuracy with the MNIST dataset on a five-qubit system.