$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
This addresses the challenge of accurate and efficient long-term probabilistic forecasting for fields like economics, energy, and transportation, representing a novel method for a known bottleneck.
The paper tackles the problem of long-term probabilistic time series forecasting by introducing K^2VAE, which uses a KoopmanNet to linearize nonlinear dynamics and a KalmanNet to refine predictions, resulting in reduced error accumulation and outperforming state-of-the-art methods in both short- and long-term forecasting.
Probabilistic Time Series Forecasting (PTSF) plays a crucial role in decision-making across various fields, including economics, energy, and transportation. Most existing methods excell at short-term forecasting, while overlooking the hurdles of Long-term Probabilistic Time Series Forecasting (LPTSF). As the forecast horizon extends, the inherent nonlinear dynamics have a significant adverse effect on prediction accuracy, and make generative models inefficient by increasing the cost of each iteration. To overcome these limitations, we introduce $K^2$VAE, an efficient VAE-based generative model that leverages a KoopmanNet to transform nonlinear time series into a linear dynamical system, and devises a KalmanNet to refine predictions and model uncertainty in such linear system, which reduces error accumulation in long-term forecasting. Extensive experiments demonstrate that $K^2$VAE outperforms state-of-the-art methods in both short- and long-term PTSF, providing a more efficient and accurate solution.