Conformal Prediction via Regression-as-Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916202591289344 |
|---|---|
| author | Guha, Etash Natarajan, Shlok Möllenhoff, Thomas Khan, Mohammad Emtiyaz Ndiaye, Eugene |
| author_facet | Guha, Etash Natarajan, Shlok Möllenhoff, Thomas Khan, Mohammad Emtiyaz Ndiaye, Eugene |
| contents | Conformal prediction (CP) for regression can be challenging, especially when the output distribution is heteroscedastic, multimodal, or skewed. Some of the issues can be addressed by estimating a distribution over the output, but in reality, such approaches can be sensitive to estimation error and yield unstable intervals.~Here, we circumvent the challenges by converting regression to a classification problem and then use CP for classification to obtain CP sets for regression.~To preserve the ordering of the continuous-output space, we design a new loss function and make necessary modifications to the CP classification techniques.~Empirical results on many benchmarks shows that this simple approach gives surprisingly good results on many practical problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08168 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Conformal Prediction via Regression-as-Classification Guha, Etash Natarajan, Shlok Möllenhoff, Thomas Khan, Mohammad Emtiyaz Ndiaye, Eugene Machine Learning Conformal prediction (CP) for regression can be challenging, especially when the output distribution is heteroscedastic, multimodal, or skewed. Some of the issues can be addressed by estimating a distribution over the output, but in reality, such approaches can be sensitive to estimation error and yield unstable intervals.~Here, we circumvent the challenges by converting regression to a classification problem and then use CP for classification to obtain CP sets for regression.~To preserve the ordering of the continuous-output space, we design a new loss function and make necessary modifications to the CP classification techniques.~Empirical results on many benchmarks shows that this simple approach gives surprisingly good results on many practical problems. |
| title | Conformal Prediction via Regression-as-Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.08168 |