$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting

TL;DR

The paper introduces $K^2$VAE, a novel VAE-based model that combines Koopman and Kalman networks to improve long-term probabilistic time series forecasting by transforming nonlinear dynamics into linear systems, enhancing accuracy and efficiency.

Contribution

It proposes a new framework integrating KoopmanNet and KalmanNet within a VAE to address long-term forecasting challenges in nonlinear time series.

Findings

$K^2$VAE outperforms existing methods in accuracy.

It reduces error accumulation in long-term forecasts.

The model is more computationally efficient.

Abstract

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.