Conformal risk control is an extension of conformal prediction for controlling risk functions beyond miscoverage. The original algorithm controls the expected value of a loss that is monotonic in a one-dimensional parameter. Here, we present risk control guarantees for generic algorithms applied to possibly non-monotonic losses with multidimensional parameters. The guarantees depend on the stability of the algorithm -- unstable algorithms have looser guarantees. We give applications of this technique to selective image classification, FDR and IOU control of tumor segmentations, and multigroup debiasing of recidivism predictions across overlapping race and sex groups using empirical risk minimization.

翻译：保形风险控制是保形预测的扩展，旨在控制除误覆盖率之外的风险函数。原始算法控制的是关于一维参数单调的损失的期望值。本文针对可能非单调且具有多维参数的损失，提出了适用于通用算法的风险控制保证。该保证取决于算法的稳定性——不稳定的算法具有更宽松的保证。我们展示了该技术在以下领域的应用：选择性图像分类、肿瘤分割的FDR与IOU控制，以及通过经验风险最小化对重叠种族与性别群体进行累犯预测的多组去偏。