论文标题
均匀收敛的样品复杂性进行数学核
Sample Complexity of Uniform Convergence for Multicalibration
论文作者
论文摘要
对机器学习系统的社会关注，尤其是在公平性方面，人们对社会关注的兴趣越来越大。多中心提供了解决群体公平性的全面方法。在这项工作中，我们解决了多核电误差，并将其从预测误差中解脱出来。取消公平度量标准（多核电）和准确性（预测错误）的重要性是由于两者之间的固有权衡以及有关“正确权衡”的社会决定（正如监管机构强加了很多次）。我们的工作给出了样本复杂性界限，以保证多核电误差的均匀收敛保证，这意味着无论准确性如何，我们都可以保证经验和（真）多核电误差是紧密的。我们强调的是我们的结果：（1）比以前的界限更一般，因为它们适用于不可知论和可实现的设置，并且不依赖于特定类型的算法（例如，派遣私有），（2）改善了先前的多核算样品复杂性界限，并且（3）意味着统一的融合为统一的融合提供了统一的校准级别的校准错误。
There is a growing interest in societal concerns in machine learning systems, especially in fairness. Multicalibration gives a comprehensive methodology to address group fairness. In this work, we address the multicalibration error and decouple it from the prediction error. The importance of decoupling the fairness metric (multicalibration) and the accuracy (prediction error) is due to the inherent trade-off between the two, and the societal decision regarding the "right tradeoff" (as imposed many times by regulators). Our work gives sample complexity bounds for uniform convergence guarantees of multicalibration error, which implies that regardless of the accuracy, we can guarantee that the empirical and (true) multicalibration errors are close. We emphasize that our results: (1) are more general than previous bounds, as they apply to both agnostic and realizable settings, and do not rely on a specific type of algorithm (such as deferentially private), (2) improve over previous multicalibration sample complexity bounds and (3) implies uniform convergence guarantees for the classical calibration error.
