Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2307.03756 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914630422495232 |
|---|---|
| author | Xu, Zhijian Zeng, Ailing Xu, Qiang |
| author_facet | Xu, Zhijian Zeng, Ailing Xu, Qiang |
| contents | 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. By discarding high-frequency components with negligible impact on time series data, FITS achieves performance comparable to state-of-the-art models for time series forecasting and anomaly detection tasks, while having a remarkably compact size of only approximately $10k$ parameters. Such a lightweight model can be easily trained and deployed in edge devices, creating opportunities for various applications. The code is available in: \url{https://github.com/VEWOXIC/FITS} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_03756 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | FITS: Modeling Time Series with $10k$ Parameters Xu, Zhijian Zeng, Ailing Xu, Qiang Machine Learning 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. By discarding high-frequency components with negligible impact on time series data, FITS achieves performance comparable to state-of-the-art models for time series forecasting and anomaly detection tasks, while having a remarkably compact size of only approximately $10k$ parameters. Such a lightweight model can be easily trained and deployed in edge devices, creating opportunities for various applications. The code is available in: \url{https://github.com/VEWOXIC/FITS} |
| title | FITS: Modeling Time Series with $10k$ Parameters |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2307.03756 |