Foundations of Sequence-to-Sequence Modeling for Time Series
This work addresses a foundational gap for researchers and practitioners in time series forecasting, offering theoretical insights to inform model selection.
The authors tackled the lack of theoretical analysis for sequence-to-sequence models in time series forecasting by providing the first such analysis, including a comparison to classical models to guide practitioners.
The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interest in the use of sequence-to-sequence models for time series forecasting. We provide the first theoretical analysis of this time series forecasting framework. We include a comparison of sequence-to-sequence modeling to classical time series models, and as such our theory can serve as a quantitative guide for practitioners choosing between different modeling methodologies.