论文标题
公制分类器取代
Metric-Fair Classifier Derandomization
论文作者
论文摘要
我们研究机器学习中分类器降低的问题：给定一个随机二进制分类器$ f：x \ to [0,1] $，采样确定性的分类器$ \ hat {f}：x \ to \ to \ {0,1 \} $，该$近似于$ f $的$ f $在任何数据分布中的$ f $。最近的工作揭示了如何有效地确定具有强大输出近似保证的随机分类器，但以个人公平为代价 - 也就是说，如果$ f $处理过类似的输入，则$ \ hat {f} $没有。在本文中，我们启动了对分类器降低的系统研究，并提供了公平保证。我们表明，先前的降低方法几乎是最大的度量 - ``随机阈值''的简单``derandomization''可实现最佳公平性保存，但输出近似较弱。然后，我们设计了一个衍生化程序，该程序在这两者之间提供了一个吸引人的权衡：如果$ f $是$α$ metric公平的公平公平的，该指标$ d $带有局部敏感性的哈希（LSH）家族，那么我们的衍生$ \ hat {f} $，具有很高的可能性，$ O（α）$ - $ o（α）$ -METRIC BEAL和$ F $ F $ f $ f $ f $。我们还证明了适用于所有（公平和不公平的）分类器降低程序的通用结果，包括偏置变化分解和各种度量公平概念之间的降低。
We study the problem of classifier derandomization in machine learning: given a stochastic binary classifier $f: X \to [0,1]$, sample a deterministic classifier $\hat{f}: X \to \{0,1\}$ that approximates the output of $f$ in aggregate over any data distribution. Recent work revealed how to efficiently derandomize a stochastic classifier with strong output approximation guarantees, but at the cost of individual fairness -- that is, if $f$ treated similar inputs similarly, $\hat{f}$ did not. In this paper, we initiate a systematic study of classifier derandomization with metric fairness guarantees. We show that the prior derandomization approach is almost maximally metric-unfair, and that a simple ``random threshold'' derandomization achieves optimal fairness preservation but with weaker output approximation. We then devise a derandomization procedure that provides an appealing tradeoff between these two: if $f$ is $α$-metric fair according to a metric $d$ with a locality-sensitive hash (LSH) family, then our derandomized $\hat{f}$ is, with high probability, $O(α)$-metric fair and a close approximation of $f$. We also prove generic results applicable to all (fair and unfair) classifier derandomization procedures, including a bias-variance decomposition and reductions between various notions of metric fairness.
