Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917352096923648 |
|---|---|
| author | Wang, Hao Pan, Licheng Lu, Yuan Chen, Zhichao Liu, Tianqiao He, Shuting Chu, Zhixuan Wen, Qingsong Li, Haoxuan Lin, Zhouchen |
| author_facet | Wang, Hao Pan, Licheng Lu, Yuan Chen, Zhichao Liu, Tianqiao He, Shuting Chu, Zhixuan Wen, Qingsong Li, Haoxuan Lin, Zhouchen |
| contents | The design of training objective is central to training time-series forecasting models. Existing training objectives such as mean squared error mostly treat each future step as an independent, equally weighted task, which we found leading to the following two issues: (1) overlook the label autocorrelation effect among future steps, leading to biased training objective; (2) fail to set heterogeneous task weights for different forecasting tasks corresponding to varying future steps, limiting the forecasting performance. To fill this gap, we propose a novel quadratic-form weighted training objective, addressing both of the issues simultaneously. Specifically, the off-diagonal elements of the weighting matrix account for the label autocorrelation effect, whereas the non-uniform diagonals are expected to match the most preferable weights of the forecasting tasks with varying future steps. To achieve this, we propose a Quadratic Direct Forecast (QDF) learning algorithm, which trains the forecast model using the adaptively updated quadratic-form weighting matrix. Experiments show that our QDF effectively improves performance of various forecast models, achieving state-of-the-art results. Code is available at https://anonymous.4open.science/r/QDF-8937. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00053 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models Wang, Hao Pan, Licheng Lu, Yuan Chen, Zhichao Liu, Tianqiao He, Shuting Chu, Zhixuan Wen, Qingsong Li, Haoxuan Lin, Zhouchen Machine Learning Artificial Intelligence The design of training objective is central to training time-series forecasting models. Existing training objectives such as mean squared error mostly treat each future step as an independent, equally weighted task, which we found leading to the following two issues: (1) overlook the label autocorrelation effect among future steps, leading to biased training objective; (2) fail to set heterogeneous task weights for different forecasting tasks corresponding to varying future steps, limiting the forecasting performance. To fill this gap, we propose a novel quadratic-form weighted training objective, addressing both of the issues simultaneously. Specifically, the off-diagonal elements of the weighting matrix account for the label autocorrelation effect, whereas the non-uniform diagonals are expected to match the most preferable weights of the forecasting tasks with varying future steps. To achieve this, we propose a Quadratic Direct Forecast (QDF) learning algorithm, which trains the forecast model using the adaptively updated quadratic-form weighting matrix. Experiments show that our QDF effectively improves performance of various forecast models, achieving state-of-the-art results. Code is available at https://anonymous.4open.science/r/QDF-8937. |
| title | Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.00053 |