papers AI Learner
The Github is limit! Click to go to the new site.

Foundations of Sequence-to-Sequence Modeling for Time Series

2019-02-26
Vitaly Kuznetsov, Zelda Mariet

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1805.03714

PDF

http://arxiv.org/pdf/1805.03714


Similar Posts

Comments