On quantum ensembles of quantum classifiers

TL;DR

This paper explores quantum ensembles of classifiers, showing that some implementations can be dequantized while others, like the Deutsch-Jozsa-based ensemble, retain quantum speedup potential for enhanced machine learning.

Contribution

It introduces a quantum ensemble framework, demonstrating dequantization of certain implementations and highlighting the quantum advantage in others using the Deutsch-Jozsa algorithm.

Findings

Accuracy-weighted quantum ensemble can be fully dequantized.

The general quantum ensemble framework includes the Deutsch-Jozsa algorithm.

Potential for quantum speedup in quantum ensemble methods.

Abstract

Quantum machine learning seeks to exploit the underlying nature of a quantum computer to enhance machine learning techniques. A particular framework uses the quantum property of superposition to store sets of parameters, thereby creating an ensemble of quantum classifiers that may be computed in parallel. The idea stems from classical ensemble methods where one attempts to build a stronger model by averaging the results from many different models. In this work, we demonstrate that a specific implementation of the quantum ensemble of quantum classifiers, called the accuracy-weighted quantum ensemble, can be fully dequantised. On the other hand, the general quantum ensemble framework is shown to contain the well-known Deutsch-Jozsa algorithm that notably provides a quantum speedup and creates the potential for a useful quantum ensemble to harness this computational advantage.