基于占用率的分位数风险控制
Occupancy-based Quantile Risk Control
另 1 家 · 查看机构详情
- Southern University of Science and Technology（南方科技大学）
- Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
- The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
- Shenzhen Loop Area Institute（深圳河套学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对现有分位数风险控制方法存在过度保守或缺乏有限样本保证的局限，提出OQRC方法，通过有序校准损失划分损失空间实现紧风险控制，在常见基准上可将风险差距降低多达78.64%。
中文摘要 AI 辅助
保形风险控制是一种用于机器学习模型安全部署的新兴框架，具有有限样本保证，为适应更广泛的风险概念，分位数风险控制将该框架扩展至基于分位数的风险度量。然而现有方法要么存在过度保守性，要么缺乏严格的有限样本保证。为解决这些局限，我们提出基于占用率的分位数风险控制（Occupancy-based Quantile Risk Control，OQRC），这是一种能提供具有有限样本有效性的紧风险控制边界的新方法。我们的核心思路是通过有序校准损失划分损失空间，将风险控制表述为有限占用率问题，具体而言，我们估计测试损失在划分后各个区间的分布，并通过每个区间内达到的最大损失对风险进行上界估计，随后选择参数λ，使得该上界以高概率1-δ不超过预定义阈值α。理论上，我们建立了有限样本保证，表明OQRC产生的紧风险控制边界以可证明的速率O_p(n^{-1/2})收敛至最优边界。大量实验证明了我们方法的有效性，在常见基准上可将风险差距降低多达78.64%。
英文摘要
Conformal risk control is an emerging framework for the safe deployment of machine learning models with finite-sample guarantees. To accommodate a broader class of risk notions, quantile risk control extends this framework to quantile-based risk measures. However, existing methods either suffer from excessive conservatism or lack rigorous finite-sample guarantees. To address these limitations, we introduce Occupancy-based Quantile Risk Control (OQRC), a novel method that provides tight risk control bounds with finite-sample validity. Our key idea is to formulate risk control as a finite-occupancy problem by partitioning the loss space with the ordered calibration losses. Specifically, we estimate the distribution of test losses across the resulting bins and upper-bound the risk by the maximum loss attained within each bin. We then select the parameter $λ$ such that this upper bound does not exceed a predefined threshold $α$ with high probability $1-δ$. Theoretically, we establish a finite-sample guarantee showing that OQRC yields tight risk control bounds that converge to the optimal bounds at a provable rate of $\mathcal{O}_ p(n^{-1/2})$. Extensive experiments demonstrate the effectiveness of our method, reducing the risk gap by up to 78.64\% on common benchmarks.
