Online Kernel Dynamic Mode Decomposition for Streaming Time Series Forecasting with Adaptive Windowing
This work addresses the problem of streaming time series forecasting for applications in constrained computing environments, offering a practical alternative to deep learning with incremental improvements in efficiency and adaptability.
The paper tackles real-time forecasting from streaming data by introducing WORK-DMD, a method that combines Random Fourier Features with online Dynamic Mode Decomposition to handle non-stationary dynamics efficiently, achieving higher accuracy than state-of-the-art online methods in experiments across benchmark datasets.
Real-time forecasting from streaming data poses critical challenges: handling non-stationary dynamics, operating under strict computational limits, and adapting rapidly without catastrophic forgetting. However, many existing approaches face trade-offs between accuracy, adaptability, and efficiency, particularly when deployed in constrained computing environments. We introduce WORK-DMD (Windowed Online Random Kernel Dynamic Mode Decomposition), a method that combines Random Fourier Features with online Dynamic Mode Decomposition to capture nonlinear dynamics through explicit feature mapping, while preserving fixed computational cost and competitive predictive accuracy across evolving data. WORK-DMD employs Sherman-Morrison updates within rolling windows, enabling continuous adaptation to evolving dynamics from only current data, eliminating the need for lengthy training or large storage requirements for historical data. Experiments on benchmark datasets across several domains show that WORK-DMD achieves higher accuracy than several state-of-the-art online forecasting methods, while requiring only a single pass through the data and demonstrating particularly strong performance in short-term forecasting. Our results show that combining kernel evaluations with adaptive matrix updates achieves strong predictive performance with minimal data requirements. This sample efficiency offers a practical alternative to deep learning for streaming forecasting applications.