Can variational quantum machine learning models beat classical approaches in time series forecasting?
This question drove the research behind our new paper, now published in Machine Learning: Science and Technology. We present a comprehensive benchmark comparing variational quantum algorithms with classical machine learning models. To ensure a fair comparison, we matched model complexities and employed rigorous hyperparameter optimization. We found that quantum models, despite their promise, often fail to outperform classical baselines of similar complexity. Our work also discusses the practical limitations and design trade-offs inherent in variational quantum methods for time series tasks.
You can find the full paper here: https://doi.org/10.1088/2632-2153/ae365f
Abstract:
Variational quantum machine learning algorithms have been proposed as promising tools for time series prediction, with the potential to handle complex sequential data more effectively than classical approaches. However, their practical advantage over established classical methods remains uncertain. In this work, we present a comprehensive benchmark study comparing a range of variational quantum algorithms and classical machine learning models for time series forecasting. We evaluate their predictive performance on three chaotic systems across 27 time series prediction tasks of varying complexity, and ensure a fair comparison through extensive hyperparameter optimization. Our results indicate that, in many cases, quantum models struggle to match the accuracy of simple classical counterparts of comparable complexity. Furthermore, we analyze the predictive performance relative to the model complexity and discuss the practical limitations of variational quantum algorithms for time series forecasting.
