发表机构
Instituto de Computação; Universidade Estadual de Campinas; Department of Computer Science; Saarland University（计算研究所; 坎皮纳斯州立大学; 计算机科学系; 萨尔兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对选择性标签下的绩效预测问题，提出基于置信区间的最坏情况目标，使重复风险最小化保持在稳定点有界距离内，实验验证其性能接近完整标签访问的RRM。
AI 中文摘要
机器学习的许多社会应用表现出绩效效应：群体行为随部署模型的变化而变化。绩效预测通过一个分布映射来研究这种交互，该映射将每个模型与其诱导的群体分布相关联。该框架的主要结果之一表明，重复风险最小化（RRM）——通过在最新数据上重新训练来更新模型——可以收敛到一个在其自身诱导分布上最小化风险的稳定模型。然而，现有分析通常假设在模型部署后可以访问完整的特征和标签分布，忽略了选择性标签的可能性：仅观察被接受子群体的标签。在这项工作中，我们形式化了带选择性标签的绩效预测，并表明仅对观察到的数据进行重新训练可能会误导重新训练过程，并破坏收敛到稳定解的保证。然后，我们提出一个基于正标签概率置信区间知识的最坏情况目标。将RRM应用于该目标使我们能够保持在真实稳定点的有界距离内。在条件标签分布的敏感性假设下，我们进一步展示了先前接受的数据如何随时间收紧这些置信区间。在具有公平正则化的贷款应用中的实验表明，我们的鲁棒优化方法在性能上与具有完整标签访问的RRM紧密匹配。
英文摘要
Many social applications of machine learning exhibit performative effects: population behavior changes in response to deployed models. Performative prediction studies this interaction through a distribution map that relates each model to the population distribution it induces. One of the main results in this framework showed that repeated risk minimization (RRM), which updates models by retraining on the most recent data, can converge to a stable model that minimizes risk on its own induced distribution. However, existing analyses typically assume access to the complete distributions of features and labels after model deployment, ignoring the possibility of selective labels: observing labels only for the accepted subset of the population. In this work, we formalize performative prediction with selective labels and show that retraining only on observed data can misguide the retraining procedure and undermine the guarantees of convergence to a stable solution. We then propose a worst-case objective based on knowledge of a confidence interval on the probability of a positive label. Applying RRM to this objective permits us to remain within a bounded distance to the true stable point. Under a sensitivity assumption on the conditional label distribution, we further show how previously accepted data can tighten these confidence intervals over time. Experiments in a lending application with fairness regularization show that our robust optimization approach closely matches the performance of RRM with complete label access.
CommentsAccepted at NeurIPS 2026. Camera-ready version
