Quantum machine learning algorithms for anomaly detection: A review

TL;DR

This review explores quantum machine learning algorithms for anomaly detection, highlighting their principles, classifications, resource requirements, and computational complexities across various disciplines.

Contribution

It systematically categorizes quantum anomaly detection algorithms and discusses their potential hardware needs and computational challenges.

Findings

Quantum algorithms can potentially accelerate anomaly detection tasks.

Different learning paradigms have distinct resource and complexity profiles.

The review maps current techniques and future hardware considerations.

Abstract

The advent of quantum computers has justified the development of quantum machine learning algorithms , based on the adaptation of the principles of machine learning to the formalism of qubits. Among such quantum algorithms, anomaly detection represents an important problem crossing several disciplines from cybersecurity, to fraud detection to particle physics. We summarize the key concepts involved in quantum computing, introducing the formal concept of quantum speed up. The review provides a structured map of anomaly detection based on quantum machine learning. We have grouped existing algorithms according to the different learning methods, namely quantum supervised, quantum unsupervised and quantum reinforcement learning, respectively. We provide an estimate of the hardware resources to provide sufficient computational power in the future. The review provides a systematic and compact understanding of the techniques belonging to each category. We eventually provide a discussion on the computational complexity of the learning methods in real application domains.