Scaling Transformers for Time Series Forecasting: Do Pretrained Large Models Outperform Small-Scale Alternatives?
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913926061490176 |
|---|---|
| author | Chakraborty, Sanjay Delibasoglu, Ibrahim Heintz, Fredrik |
| author_facet | Chakraborty, Sanjay Delibasoglu, Ibrahim Heintz, Fredrik |
| contents | Large pre-trained models have demonstrated remarkable capabilities across domains, but their effectiveness in time series forecasting remains understudied. This work empirically examines whether pre-trained large-scale time series models (LSTSMs) trained on diverse datasets can outperform traditional non-pretrained small-scale transformers in forecasting tasks. We analyze state-of-the-art (SOTA) pre-trained universal time series models (e.g., Moirai, TimeGPT) alongside conventional transformers, evaluating accuracy, computational efficiency, and interpretability across multiple benchmarks. Our findings reveal the strengths and limitations of pre-trained LSTSMs, providing insights into their suitability for time series tasks compared to task-specific small-scale architectures. The results highlight scenarios where pretraining offers advantages and where simpler models remain competitive. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02907 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scaling Transformers for Time Series Forecasting: Do Pretrained Large Models Outperform Small-Scale Alternatives? Chakraborty, Sanjay Delibasoglu, Ibrahim Heintz, Fredrik Machine Learning Large pre-trained models have demonstrated remarkable capabilities across domains, but their effectiveness in time series forecasting remains understudied. This work empirically examines whether pre-trained large-scale time series models (LSTSMs) trained on diverse datasets can outperform traditional non-pretrained small-scale transformers in forecasting tasks. We analyze state-of-the-art (SOTA) pre-trained universal time series models (e.g., Moirai, TimeGPT) alongside conventional transformers, evaluating accuracy, computational efficiency, and interpretability across multiple benchmarks. Our findings reveal the strengths and limitations of pre-trained LSTSMs, providing insights into their suitability for time series tasks compared to task-specific small-scale architectures. The results highlight scenarios where pretraining offers advantages and where simpler models remain competitive. |
| title | Scaling Transformers for Time Series Forecasting: Do Pretrained Large Models Outperform Small-Scale Alternatives? |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.02907 |