BriefGPT.xyz
Sep, 2024
调整回归模型以进行条件不确定性校准
Adjusting Regression Models for Conditional Uncertainty Calibration
HTML
PDF
Ruijiang Gao, Mingzhang Yin, James McInerney, Nathan Kallus
TL;DR
本研究针对传统的保形预测方法在条件覆盖保证方面的不足，提出了一种新算法以改善条件覆盖。通过建立条件覆盖与名义覆盖率之间的失误覆盖差界限，提供了一个端到端的算法，实证结果表明该方法在合成和真实数据集上表现出色。
Abstract
Conformal Prediction
methods have finite-sample distribution-free marginal coverage guarantees. However, they generally do not offer
Conditional Coverage
guarantees, which can be important for high-stakes decisio
→