Quantum-enhanced machine learning

TL;DR

This paper presents a comprehensive quantum information-based framework for all main types of machine learning, demonstrating potential quadratic and exponential improvements in efficiency and performance, especially in reinforcement learning.

Contribution

It introduces a systematic approach to quantum enhancements across supervised, unsupervised, and reinforcement learning, including novel methods for reinforcement learning.

Findings

Quadratic improvements in learning efficiency.

Exponential performance gains over limited time periods.

Applicable to a broad class of learning problems.

Abstract

The emerging field of quantum machine learning has the potential to substantially aid in the problems and scope of artificial intelligence. This is only enhanced by recent successes in the field of classical machine learning. In this work we propose an approach for the systematic treatment of machine learning, from the perspective of quantum information. Our approach is general and covers all three main branches of machine learning: supervised, unsupervised and reinforcement learning. While quantum improvements in supervised and unsupervised learning have been reported, reinforcement learning has received much less attention. Within our approach, we tackle the problem of quantum enhancements in reinforcement learning as well, and propose a systematic scheme for providing improvements. As an example, we show that quadratic improvements in learning efficiency, and exponential improvements in performance over limited time periods, can be obtained for a broad class of learning problems.