FITS: Modeling Time Series with $10k$ Parameters

Abstract

In this paper, we introduce FITS, a lightweight yet powerful model for time series analysis. Unlike existing models that directly process raw time-domain data, FITS operates on the principle that time series can be manipulated through interpolation in the complex frequency domain, achieving performance comparable to state-of-the-art models for time series forecasting and anomaly detection tasks. Notably, FITS accomplishes this with a svelte profile of just about $10k$ parameters, making it ideally suited for edge devices and paving the way for a wide range of applications. The code is available for review at: \url{https://anonymous.4open.science/r/FITS}.

Cite

Text

Xu et al. "FITS: Modeling Time Series with $10k$ Parameters." International Conference on Learning Representations, 2024.

Markdown

[Xu et al. "FITS: Modeling Time Series with $10k$ Parameters." International Conference on Learning Representations, 2024.](https://mlanthology.org/iclr/2024/xu2024iclr-fits/)

BibTeX

@inproceedings{xu2024iclr-fits,
  title     = {{FITS: Modeling Time Series with $10k$ Parameters}},
  author    = {Xu, Zhijian and Zeng, Ailing and Xu, Qiang},
  booktitle = {International Conference on Learning Representations},
  year      = {2024},
  url       = {https://mlanthology.org/iclr/2024/xu2024iclr-fits/}
}