Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.07093 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912943839379456 |
|---|---|
| author | Yao, Yunzhen He, Lie Gastpar, Michael |
| author_facet | Yao, Yunzhen He, Lie Gastpar, Michael |
| contents | Conformal prediction provides prediction sets with coverage guarantees. The informativeness of conformal prediction depends on its efficiency, typically quantified by the expected size of the prediction set. Prior work on the efficiency of conformalized regression commonly treats the miscoverage level $α$ as a fixed constant. In this work, we establish non-asymptotic bounds on the deviation of the prediction set length from the oracle interval length for conformalized quantile and median regression trained via SGD, under mild assumptions on the data distribution. Our bounds of order $\mathcal{O}(1/\sqrt{n} + 1/(α^2 n) + 1/\sqrt{m} + \exp(-α^2 m))$ capture the joint dependence of efficiency on the proper training set size $n$, the calibration set size $m$, and the miscoverage level $α$. The results identify phase transitions in convergence rates across different regimes of $α$, offering guidance for allocating data to control excess prediction set length. Empirical results are consistent with our theoretical findings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07093 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Non-Asymptotic Analysis of Efficiency in Conformalized Regression Yao, Yunzhen He, Lie Gastpar, Michael Machine Learning Conformal prediction provides prediction sets with coverage guarantees. The informativeness of conformal prediction depends on its efficiency, typically quantified by the expected size of the prediction set. Prior work on the efficiency of conformalized regression commonly treats the miscoverage level $α$ as a fixed constant. In this work, we establish non-asymptotic bounds on the deviation of the prediction set length from the oracle interval length for conformalized quantile and median regression trained via SGD, under mild assumptions on the data distribution. Our bounds of order $\mathcal{O}(1/\sqrt{n} + 1/(α^2 n) + 1/\sqrt{m} + \exp(-α^2 m))$ capture the joint dependence of efficiency on the proper training set size $n$, the calibration set size $m$, and the miscoverage level $α$. The results identify phase transitions in convergence rates across different regimes of $α$, offering guidance for allocating data to control excess prediction set length. Empirical results are consistent with our theoretical findings. |
| title | Non-Asymptotic Analysis of Efficiency in Conformalized Regression |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.07093 |