WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting
This addresses overfitting issues in time series forecasting for applications like traffic and finance, but it is an incremental improvement as it builds on existing regularization methods.
The paper tackles unstable training and overfitting in deep learning for time series forecasting by introducing dynamic error bounds on training loss, resulting in significant improvements in generalization over existing models, including state-of-the-art ones.
Time series forecasting has become a critical task due to its high practicality in real-world applications such as traffic, energy consumption, economics and finance, and disease analysis. Recent deep-learning-based approaches have shown remarkable success in time series forecasting. Nonetheless, due to the dynamics of time series data, deep networks still suffer from unstable training and overfitting. Inconsistent patterns appearing in real-world data lead the model to be biased to a particular pattern, thus limiting the generalization. In this work, we introduce the dynamic error bounds on training loss to address the overfitting issue in time series forecasting. Consequently, we propose a regularization method called WaveBound which estimates the adequate error bounds of training loss for each time step and feature at each iteration. By allowing the model to focus less on unpredictable data, WaveBound stabilizes the training process, thus significantly improving generalization. With the extensive experiments, we show that WaveBound consistently improves upon the existing models in large margins, including the state-of-the-art model.