个体偏差和不公平性的ML模型审计
Auditing ML Models for Individual Bias and Unfairness
摘要:
我们考虑审计ML模型的个人偏见/不公平性的任务。我们正式的任务在一个优化问题,并开发了一套推理工具的最佳值。我们的工具使我们能够获得渐近置信区间和假设检验,覆盖目标/控制第一类错误率。为了证明我们的工具的实用性,我们用它们来揭示性别和种族偏见在Northpointe的COMPAS累犯预测工具。
英文摘要:
We consider the task of auditing ML models for individual bias/unfairness. We formalize the task in an optimization problem and develop a suite of inferential tools for the optimal value. Our tools permit us to obtain asymptotic confidence intervals and hypothesis tests that cover the target/control the Type I error rate exactly. To demonstrate the utility of our tools, we use them to reveal the gender and racial biases in Northpointe's COMPAS recidivism prediction instrument.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。