Testing the Fairness-Accuracy Improvability of Algorithms
检验算法能否在不损失准确性的情况下改善公平性AI 解读 ↓
← 返回论文列表与筛选
阅读说明
本页整理公开书目信息，不生成学术质量评分。AI 解读根据题名及所注明的摘要或原文片段生成，未完成全文核验，可能有误；具体假设、证明与结论请核对原文。摘要保留来源文本，未经模型改写。
DOI 首次登记不等于接收或发表日期。部分更正、评论等条目没有独立摘要；缺少可靠材料时保留待补状态。
本页为预印本版本；arXiv 收录、作者填写的期刊信息以及作者既有发表经历，都不单独证明本篇已接收。作者发表记录按 OpenAlex 身份与完整姓名、本站覆盖期刊 ISSN 及正式卷期核对，只展示已核实例，档案仍可能误合并。
引用量采用 OpenAlex 单条关联记录，不合计多个记录；关联记录可能包含正式发表版本，不等于此版本单独引用。缺失不视为零，引用指标不代表论文质量。
关注作者按书目中的完整姓名匹配，同名和姓名变体需人工辨别。相关论文先按共享细分方向和具体方法排列，再参考通用方法与发表日期。
分类依据与纠错
AI 根据所提供的论文材料归类：摘要研究通用算法公平性与多目标可改进性的检验，未明确涉及所列因果、选择或金融等细分方向。
反馈分类问题正在核对关联版本…
代码、数据与补充材料
正在核对对应版本的资源…
检验算法能否在不损失准确性的情况下改善公平性
- 研究问题
- 如何正式检验一个算法是否存在更公平且不损害其他预定目标的替代方案，从而评估差异影响是否具有必要性？
- 方法与思路
- 作者提出允许算法空间外生约束的计量检验，研究大样本有效性和一致性，并用政策制定者与分析者博弈讨论抗操纵性质。
- 材料陈述的贡献
- 摘要称该检验易于实施且可适配外生约束，并在医疗算法应用中量化维持预测准确性时能够减少的群体差异影响。
- 阅读关注点
- 应核对公平性指标、不可损害目标的定义、可行算法集合，以及检验假设方向、候选方案搜索与抗操纵结论的条件。
- 阅读边界
- 这是 arXiv 预印本，同行评审与期刊接收未核实；摘要未列明有效性条件或改善幅度，统计结论也不能直接代替法律判断。
原文摘要
Many organizations use algorithms that have a disparate impact, i.e., the benefits or harms of the algorithm fall disproportionately on certain social groups. Addressing an algorithm's disparate impact can be challenging, however, because it is often unclear whether it is possible to reduce this impact without sacrificing other objectives of the organization, such as accuracy or profit. Establishing the improvability of algorithms with respect to multiple criteria is of both conceptual and practical interest: in many settings, disparate impact that would otherwise be prohibited under US federal law is permissible if it is necessary to achieve a legitimate business interest. The question is how a policy-maker can formally substantiate, or refute, this "necessity" defense. In this paper, we provide an econometric framework for testing the hypothesis that it is possible to improve on the fairness of an algorithm without compromising on other pre-specified objectives. Our proposed test is simple to implement and can be applied under any exogenous constraint on the algorithm space. We establish the large-sample validity and consistency of our test, and microfound the test's robustness to manipulation based on a game between a policymaker and the analyst. Finally, we apply our approach to evaluate a healthcare algorithm originally considered by Obermeyer et al. (2019), and quantify the extent to which the algorithm's disparate impact can be reduced without compromising the accuracy of its predictions.