A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929655794106368 |
|---|---|
| author | Xu, Jingjing Wu, Caesar Li, Yuan-Fang Danoy, Grégoire Bouvry, Pascal |
| author_facet | Xu, Jingjing Wu, Caesar Li, Yuan-Fang Danoy, Grégoire Bouvry, Pascal |
| contents | Transformer-based models for time series forecasting (TSF) have attracted significant attention in recent years due to their effectiveness and versatility. However, these models often require extensive hyperparameter optimization (HPO) to achieve the best possible performance, and a unified pipeline for HPO in transformer-based TSF remains lacking. In this paper, we present one such pipeline and conduct extensive experiments on several state-of-the-art (SOTA) transformer-based TSF models. These experiments are conducted on standard benchmark datasets to evaluate and compare the performance of different models, generating practical insights and examples. Our pipeline is generalizable beyond transformer-based architectures and can be applied to other SOTA models, such as Mamba and TimeMixer, as demonstrated in our experiments. The goal of this work is to provide valuable guidance to both industry practitioners and academic researchers in efficiently identifying optimal hyperparameters suited to their specific domain applications. The code and complete experimental results are available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models Xu, Jingjing Wu, Caesar Li, Yuan-Fang Danoy, Grégoire Bouvry, Pascal Machine Learning Artificial Intelligence Transformer-based models for time series forecasting (TSF) have attracted significant attention in recent years due to their effectiveness and versatility. However, these models often require extensive hyperparameter optimization (HPO) to achieve the best possible performance, and a unified pipeline for HPO in transformer-based TSF remains lacking. In this paper, we present one such pipeline and conduct extensive experiments on several state-of-the-art (SOTA) transformer-based TSF models. These experiments are conducted on standard benchmark datasets to evaluate and compare the performance of different models, generating practical insights and examples. Our pipeline is generalizable beyond transformer-based architectures and can be applied to other SOTA models, such as Mamba and TimeMixer, as demonstrated in our experiments. The goal of this work is to provide valuable guidance to both industry practitioners and academic researchers in efficiently identifying optimal hyperparameters suited to their specific domain applications. The code and complete experimental results are available on GitHub. |
| title | A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2501.01394 |