Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.06390 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912401349148672 |
|---|---|
| author | English, Eshant Wong-Toi, Eliot Fontana, Matteo Mandt, Stephan Smyth, Padhraic Lippert, Christoph |
| author_facet | English, Eshant Wong-Toi, Eliot Fontana, Matteo Mandt, Stephan Smyth, Padhraic Lippert, Christoph |
| contents | Conformal prediction provides machine learning models with prediction sets that offer theoretical guarantees, but the underlying assumption of exchangeability limits its applicability to time series data. Furthermore, existing approaches struggle to handle multi-step ahead prediction tasks, where uncertainty estimates across multiple future time points are crucial. We propose JANET (Joint Adaptive predictioN-region Estimation for Time-series), a novel framework for constructing conformal prediction regions that are valid for both univariate and multivariate time series. JANET generalises the inductive conformal framework and efficiently produces joint prediction regions with controlled K-familywise error rates, enabling flexible adaptation to specific application needs. Our empirical evaluation demonstrates JANET's superior performance in multi-step prediction tasks across diverse time series datasets, highlighting its potential for reliable and interpretable uncertainty quantification in sequential data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06390 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | JANET: Joint Adaptive predictioN-region Estimation for Time-series English, Eshant Wong-Toi, Eliot Fontana, Matteo Mandt, Stephan Smyth, Padhraic Lippert, Christoph Machine Learning Methodology Conformal prediction provides machine learning models with prediction sets that offer theoretical guarantees, but the underlying assumption of exchangeability limits its applicability to time series data. Furthermore, existing approaches struggle to handle multi-step ahead prediction tasks, where uncertainty estimates across multiple future time points are crucial. We propose JANET (Joint Adaptive predictioN-region Estimation for Time-series), a novel framework for constructing conformal prediction regions that are valid for both univariate and multivariate time series. JANET generalises the inductive conformal framework and efficiently produces joint prediction regions with controlled K-familywise error rates, enabling flexible adaptation to specific application needs. Our empirical evaluation demonstrates JANET's superior performance in multi-step prediction tasks across diverse time series datasets, highlighting its potential for reliable and interpretable uncertainty quantification in sequential data. |
| title | JANET: Joint Adaptive predictioN-region Estimation for Time-series |
| topic | Machine Learning Methodology |
| url | https://arxiv.org/abs/2407.06390 |