Foundations of SequencetoSequence Modeling for Time Series
[edit]
Proceedings of Machine Learning Research, PMLR 89:408417, 2019.
Abstract
The availability of large amounts of time series data, paired with the performance of deeplearning algorithms on a broad class of problems, has recently led to significant interest in the use of sequencetosequence models for time series forecasting. We provide the first theoretical analysis of this time series forecasting framework. We include a comparison of sequencetosequence modeling to classical time series models, and as such our theory can serve as a quantitative guide for practitioners choosing between different modeling methodologies.
Related Material


