Applying Quantum Autoencoders for Time Series Anomaly Detection

TL;DR

This paper investigates the use of quantum autoencoders for time series anomaly detection, demonstrating their superior performance and efficiency over classical autoencoders through simulation and real quantum hardware experiments.

Contribution

It introduces the application of quantum autoencoders to time series anomaly detection and compares their effectiveness with classical methods using simulation and hardware tests.

Findings

Quantum autoencoders outperform classical autoencoders in anomaly detection.

They use significantly fewer parameters and training iterations.

Quantum autoencoders achieve comparable results on real hardware.

Abstract

Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition or medical diagnosis. Several algorithms have been introduced using classical computing approaches. However, using quantum computing for solving anomaly detection problems in time series data is a widely unexplored research field. This paper explores the application of quantum autoencoders to time series anomaly detection. We investigate two primary techniques for classifying anomalies: (1) Analyzing the reconstruction error generated by the quantum autoencoder and (2) latent representation analysis. Our simulated experimental results, conducted across various ansaetze, demonstrate that quantum autoencoders consistently outperform classical deep learning-based autoencoders across multiple datasets. Specifically, quantum autoencoders achieve superior anomaly detection performance while utilizing 60-230 times fewer parameters and requiring five times fewer training iterations. In addition, we implement our quantum encoder on real quantum hardware. Our experimental results demonstrate that quantum autoencoders achieve anomaly detection performance on par with their simulated counterparts.