PAC Off-Policy Prediction of Contextual Bandits
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908460600262656 |
|---|---|
| author | Wan, Yilong Li, Yuqiang Wu, Xianyi |
| author_facet | Wan, Yilong Li, Yuqiang Wu, Xianyi |
| contents | This paper investigates off-policy evaluation in contextual bandits, aiming to quantify the performance of a target policy using data collected under a different and potentially unknown behavior policy. Recently, methods based on conformal prediction have been developed to construct reliable prediction intervals that guarantee marginal coverage in finite samples, making them particularly suited for safety-critical applications. To further achieve coverage conditional on a given offline data set, we propose a novel algorithm that constructs probably approximately correct prediction intervals. Our method builds upon a PAC-valid conformal prediction framework, and we strengthen its theoretical guarantees by establishing PAC-type bounds on coverage. We analyze both finite-sample and asymptotic properties of the proposed method, and compare its empirical performance with existing methods in simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16236 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PAC Off-Policy Prediction of Contextual Bandits Wan, Yilong Li, Yuqiang Wu, Xianyi Machine Learning This paper investigates off-policy evaluation in contextual bandits, aiming to quantify the performance of a target policy using data collected under a different and potentially unknown behavior policy. Recently, methods based on conformal prediction have been developed to construct reliable prediction intervals that guarantee marginal coverage in finite samples, making them particularly suited for safety-critical applications. To further achieve coverage conditional on a given offline data set, we propose a novel algorithm that constructs probably approximately correct prediction intervals. Our method builds upon a PAC-valid conformal prediction framework, and we strengthen its theoretical guarantees by establishing PAC-type bounds on coverage. We analyze both finite-sample and asymptotic properties of the proposed method, and compare its empirical performance with existing methods in simulations. |
| title | PAC Off-Policy Prediction of Contextual Bandits |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.16236 |