解决预测影响结果的问题，让模型在动态环境中依然可靠。
Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity
- 提出迭代校准方法，确保预测和风险控制同步优化
- 在信用违约预测任务中验证框架有效，保障决策可靠性
- 首个在可表演性下提供理论保证的风险控制方案
校准黑箱机器学习模型以实现风险控制，是确保可靠决策的关键。现有研究多关注在固定、静态且未知的数据生成分布下，使模型预测满足有限样本的统计保证。然而，预测支持的决策可能影响其试图预测的结果，这种现象称为预测的可表演性，常见于社会科学与经济学领域。本文提出 Performative Risk Control 框架，在可表演性条件下实现可证明理论保障的风险控制。具体而言，我们设计了一种迭代精炼的校准过程，确保预测质量持续提升且风险始终可控。我们还研究了不同风险度量与尾部界限的选择。最后，在信用违约预测任务上通过数值实验验证了该框架的有效性。据我们所知，这是首个研究可表演性下统计严谨风险控制的工作，将为各类策略操纵提供重要防护。
原文摘要 · Abstract (English)
Calibrating blackbox machine learning models to achieve risk control is crucial to ensure reliable decision-making. A rich line of literature has been studying how to calibrate a model so that its predictions satisfy explicit finite-sample statistical guarantees under a fixed, static, and unknown data-generating distribution. However, prediction-supported decisions may influence the outcome they aim to predict, a phenomenon named performativity of predictions, which is commonly seen in social science and economics. In this paper, we introduce Performative Risk Control, a framework to calibrate models to achieve risk control under performativity with provable theoretical guarantees. Specifically, we provide an iteratively refined calibration process, where we ensure the predictions are improved and risk-controlled throughout the process. We also study different types of risk measures and choices of tail bounds. Lastly, we demonstrate the effectiveness of our framework by numerical experiments on the task of predicting credit default risk. To the best of our knowledge, this work is the first one to study statistically rigorous risk control under performativity, which will serve as an important safeguard against a wide range of strategic manipulation in decision-making processes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。