Quantum ensembles of quantum classifiers

TL;DR

This paper introduces quantum ensembles of classifiers, enabling large-scale, parallel quantum decision-making that can improve classification performance without individual training, with implications for quantum and classical machine learning.

Contribution

It proposes a novel framework for quantum classifier ensembles that operate in parallel and do not require training of individual classifiers, expanding quantum machine learning capabilities.

Findings

Enables exponentially large quantum classifier ensembles

Demonstrates performance-weighted ensemble analysis

Bridges quantum and classical machine learning methods

Abstract

Quantum machine learning witnesses an increasing amount of quantum algorithms for data-driven decision making, a problem with potential applications ranging from automated image recognition to medical diagnosis. Many of those algorithms are implementations of quantum classifiers, or models for the classification of data inputs with a quantum computer. Following the success of collective decision making with ensembles in classical machine learning, this paper introduces the concept of quantum ensembles of quantum classifiers. Creating the ensemble corresponds to a state preparation routine, after which the quantum classifiers are evaluated in parallel and their combined decision is accessed by a single-qubit measurement. This framework naturally allows for exponentially large ensembles in which -- similar to Bayesian learning -- the individual classifiers do not have to be trained. As an example, we analyse an exponentially large quantum ensemble in which each classifier is weighed according to its performance in classifying the training data, leading to new results for quantum as well as classical machine learning.