跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20387 · v1

Generalized Prediction Set with Bandit Feedback

首次提交 2026-11-16 09:27
版本更新 2026-11-16 09:27
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

In high-stakes environments where uncertainties abound, set-valued prediction offers a cautious and robust mechanism by presenting multiple potential labels as the prediction for each test instance to mitigate the potential risk associated with prediction errors. Yet, integrating this paradigm with out-of-distribution (OOD) detection remains scarcely explored in such settings as online learning with bandit feedback. The bandit feedback mechanism informs the learner about the correctness of the pulled arm/action instead of the explicit ground truth label, leaving the true class label unknown when an incorrect action is taken. To address this challenge, we introduce BanditGPS which conducts set-valued prediction with OOD detection in the bandit feedback setting, using an estimation to the ground truth of class labels. BanditGPS achieves three objectives: render small/informative prediction sets, enhance the OOD detection performance, and control the recall for all normal classes to meet prescribed requirements. Our approach is characterized by the loss function, which trades off between high OOD detection and small prediction sets. Theoretically, we prove that the convergence rate of the regret is O~(T−1/2)\tilde{\mathcal{O}}(T^{-1/2}). The empirical results further show that BanditGPS effectively controls the recalls with promising performances on OOD detection and informative prediction.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-16 09:27 · 最新观测版本

Generalized Prediction Set with Bandit Feedback

In high-stakes environments where uncertainties abound, set-valued prediction offers a cautious and robust mechanism by presenting multiple potential labels as the prediction for each test instance to mitigate the potential risk associated with prediction errors. Yet, integrating this paradigm with out-of-distribution (OOD) detection remains scarcely explored in such settings as online learning with bandit feedback. The bandit feedback mechanism informs the learner about the correctness of the pulled arm/action instead of the explicit ground truth label, leaving the true class label unknown when an incorrect action is taken. To address this challenge, we introduce BanditGPS which conducts set-valued prediction with OOD detection in the bandit feedback setting, using an estimation to the ground truth of class labels. BanditGPS achieves three objectives: render small/informative prediction sets, enhance the OOD detection performance, and control the recall for all normal classes to meet prescribed requirements. Our approach is characterized by the loss function, which trades off between high OOD detection and small prediction sets. Theoretically, we prove that the convergence rate of the regret is O~(T−1/2)\tilde{\mathcal{O}}(T^{-1/2}). The empirical results further show that BanditGPS effectively controls the recalls with promising performances on OOD detection and informative prediction.

查看此版本解读 →查看此版本原文 ↗