Foundations of Sequence-to-Sequence Modeling for Time Series

@InProceedings{pmlr-v89-mariet19a,
  title = 	 {Foundations of Sequence-to-Sequence Modeling for Time Series},
  author =       {Mariet, Zelda and Kuznetsov, Vitaly},
  booktitle = 	 {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics},
  pages = 	 {408--417},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Sugiyama, Masashi},
  volume = 	 {89},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {16--18 Apr},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v89/mariet19a/mariet19a.pdf},
  url = 	 {https://proceedings.mlr.press/v89/mariet19a.html},
  abstract = 	 {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.}
}