Quantum machine learning: a classical perspective

TL;DR

This paper reviews quantum machine learning from a classical perspective, discussing its potential advantages, limitations, and practical challenges in integrating quantum algorithms with classical machine learning.

Contribution

It provides a comprehensive overview of quantum machine learning, clarifies its limitations, compares it with classical methods, and discusses practical issues like data encoding.

Findings

Quantum algorithms have potential advantages but face significant limitations.

Noise and hard problems are promising directions for quantum ML.

Practical data encoding into quantum form remains a key challenge.

Abstract

Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning techniques to impressive results in regression, classification, data-generation and reinforcement learning tasks. Despite these successes, the proximity to the physical limits of chip fabrication alongside the increasing size of datasets are motivating a growing number of researchers to explore the possibility of harnessing the power of quantum computation to speed-up classical machine learning algorithms. Here we review the literature in quantum machine learning and discuss perspectives for a mixed readership of classical machine learning and quantum computation experts. Particular emphasis will be placed on clarifying the limitations of quantum algorithms, how they compare with their best classical counterparts and why quantum resources are expected to provide advantages for learning problems. Learning in the presence of noise and certain computationally hard problems in machine learning are identified as promising directions for the field. Practical questions, like how to upload classical data into quantum form, will also be addressed.