Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers

TL;DR

This paper explores how near-term quantum computers can enhance complex machine learning tasks, especially generative models, through hybrid quantum-classical approaches like the quantum-assisted Helmholtz machine, addressing current limitations.

Contribution

It introduces the quantum-assisted Helmholtz machine (QAHM), a hybrid framework leveraging small quantum devices for high-dimensional unsupervised learning, focusing on practical near-term applications.

Findings

QAHM can handle high-dimensional continuous data.

Hybrid quantum-classical methods are promising for near-term ML.

Focus on generative models offers new opportunities for quantum advantage.

Abstract

With quantum computing technologies nearing the era of commercialization and quantum supremacy, machine learning (ML) appears as one of the promising "killer" applications. Despite significant effort, there has been a disconnect between most quantum ML proposals, the needs of ML practitioners, and the capabilities of near-term quantum devices to demonstrate quantum enhancement in the near future. In this contribution to the focus collection on "What would you do with 1000 qubits?", we provide concrete examples of intractable ML tasks that could be enhanced with near-term devices. We argue that to reach this target, the focus should be on areas where ML researchers are struggling, such as generative models in unsupervised and semi-supervised learning, instead of the popular and more tractable supervised learning techniques. We also highlight the case of classical datasets with potential quantum-like statistical correlations where quantum models could be more suitable. We focus on hybrid quantum-classical approaches and illustrate some of the key challenges we foresee for near-term implementations. Finally, we introduce the quantum-assisted Helmholtz machine (QAHM), an attempt to use near-term quantum devices to tackle high-dimensional datasets of continuous variables. Instead of using quantum computers to assist deep learning, as previous approaches do, the QAHM uses deep learning to extract a low-dimensional binary representation of data, suitable for relatively small quantum processors which can assist the training of an unsupervised generative model. Although we illustrate this concept on a quantum annealer, other quantum platforms could benefit as well from this hybrid quantum-classical framework.