任意时间有效的保形风险控制
Anytime-Valid Conformal Risk Control
Bror Hultberg · Dave Zachariah · Ant\^onio H. Ribeiro
中文摘要
预测集为预测任务中的不确定性量化提供了一种手段。利用留出的校准数据,保形预测(conformal prediction)与风险控制能以计算高效的方式生成具有统计有效误差控制的预测集。然而在标准表述中,误差仅在固定大小的众多可能校准数据集上平均受控。本文将控制扩展为:在累积增长的校准数据集上,于任意时间点以高概率保持有效。我们通过基于分位数的论证推导出此类保证,并说明所提框架适用于涉及分布偏移(distribution shift)的场景。进一步表明,我们的保证是渐近紧的,即风险从下方收敛到目标水平,且修正速率无法改进。最后,通过模拟和真实数值示例展示了方法的实际性能。
关键要点
- 01标准保形风险控制仅在固定大小校准集上平均控制误差,无法保证任意时间点有效。
- 02利用分位数论证,将误差控制扩展为在累积增长校准集上以高概率于任意时刻成立。
- 03框架适用于分布偏移场景,并证明风险从下方渐近收敛到目标水平且修正速率不可改进。
- 04通过模拟与真实数值示例验证了方法的实际性能。
解读
尚无解读。
原始英文摘要
arXiv:2602.04364v2 Announce Type: replace Abstract: Prediction sets provide a means of quantifying the uncertainty in predictive tasks. Using held out calibration data, conformal prediction and risk control can produce prediction sets that exhibit statistically valid error control in a computationally efficient manner. However, in the standard formulations, the error is only controlled on average over many possible calibration datasets of fixed size. In this paper, we extend the control to remain valid with high probability over a cumulatively growing calibration dataset at any time point. We derive such guarantees using quantile-based arguments and illustrate the applicability of the proposed framework to settings involving distribution shift. We further show that our guarantees are asymptotically tight, in the sense that the risks converge to the target level from below, and that the rate of our correction cannot be improved. Finally, we demonstrate the practical performance of our methods through both simulations and real-world numerical examples.