English

Deep Factors for Forecasting

Machine Learning 2019-05-30 v1 Machine Learning

Abstract

Producing probabilistic forecasts for large collections of similar and/or dependent time series is a practically relevant and challenging task. Classical time series models fail to capture complex patterns in the data, and multivariate techniques struggle to scale to large problem sizes. Their reliance on strong structural assumptions makes them data-efficient, and allows them to provide uncertainty estimates. The converse is true for models based on deep neural networks, which can learn complex patterns and dependencies given enough data. In this paper, we propose a hybrid model that incorporates the benefits of both approaches. Our new method is data-driven and scalable via a latent, global, deep component. It also handles uncertainty through a local classical model. We provide both theoretical and empirical evidence for the soundness of our approach through a necessary and sufficient decomposition of exchangeable time series into a global and a local part. Our experiments demonstrate the advantages of our model both in term of data efficiency, accuracy and computational complexity.

Keywords

Cite

@article{arxiv.1905.12417,
  title  = {Deep Factors for Forecasting},
  author = {Yuyang Wang and Alex Smola and Danielle C. Maddix and Jan Gasthaus and Dean Foster and Tim Januschowski},
  journal= {arXiv preprint arXiv:1905.12417},
  year   = {2019}
}

Comments

http://proceedings.mlr.press/v97/wang19k/wang19k.pdf. arXiv admin note: substantial text overlap with arXiv:1812.00098

R2 v1 2026-06-23T09:31:33.843Z