Tailored Forecasting from Short Time Series via Meta-learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915417925091328 |
|---|---|
| author | Norton, Declan A. Ott, Edward Pomerance, Andrew Hunt, Brian Girvan, Michelle |
| author_facet | Norton, Declan A. Ott, Edward Pomerance, Andrew Hunt, Brian Girvan, Michelle |
| contents | Machine learning models can effectively forecast dynamical systems from time-series data, but they typically require large amounts of past data, making forecasting particularly challenging for systems with limited history. To overcome this, we introduce Meta-learning for Tailored Forecasting using Related Time Series (METAFORS), which generalizes knowledge across systems to enable forecasting in data-limited scenarios. By learning from a library of models trained on longer time series from potentially related systems, METAFORS builds and initializes a model tailored to short time-series data from the system of interest. Using a reservoir computing implementation and testing on simulated chaotic systems, we demonstrate that METAFORS can reliably predict both short-term dynamics and long-term statistics without requiring contextual labels. We see this even when test and related systems exhibit substantially different behaviors, highlighting METAFORS' strengths in data-limited scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16325 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tailored Forecasting from Short Time Series via Meta-learning Norton, Declan A. Ott, Edward Pomerance, Andrew Hunt, Brian Girvan, Michelle Machine Learning Chaotic Dynamics Computational Physics Machine learning models can effectively forecast dynamical systems from time-series data, but they typically require large amounts of past data, making forecasting particularly challenging for systems with limited history. To overcome this, we introduce Meta-learning for Tailored Forecasting using Related Time Series (METAFORS), which generalizes knowledge across systems to enable forecasting in data-limited scenarios. By learning from a library of models trained on longer time series from potentially related systems, METAFORS builds and initializes a model tailored to short time-series data from the system of interest. Using a reservoir computing implementation and testing on simulated chaotic systems, we demonstrate that METAFORS can reliably predict both short-term dynamics and long-term statistics without requiring contextual labels. We see this even when test and related systems exhibit substantially different behaviors, highlighting METAFORS' strengths in data-limited scenarios. |
| title | Tailored Forecasting from Short Time Series via Meta-learning |
| topic | Machine Learning Chaotic Dynamics Computational Physics |
| url | https://arxiv.org/abs/2501.16325 |