Equal Opportunity in Online Classification with Partial Feedback
Equal Opportunity in Online Classification with Partial Feedback
复制标题
部分反馈的在线分类机会均等
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Zhiwei Steven Wu
中科院分区：
文献类型：
--
作者：
Yahav Bechavod;Katrina Ligett;Aaron Roth;Bo Waggoner;Zhiwei Steven Wu
我们研究了一个带有部分反馈的在线分类问题，其中每个人从固定但未知的分布一次到达一个，并且必须被分类为正的或负的。我们的算法只观察到一个人的真实标签，如果他们被给予肯定的分类。这种设置抓住了许多关注公平的分类问题：例如，在刑事累犯预测中，只有在囚犯获释的情况下才会观察到累犯；在贷款申请中，只有在发放贷款的情况下才会观察到贷款偿还。我们要求我们的算法满足常见的统计公平性约束(例如，均衡假阳性或负率--在Hardt等人中被引入为“机会均等”)。(2016))在每一轮，关于基本分配。我们给出了这个约束代价的上界和下界(并且证明了它是温和的)，并给出了一个达到这个上界的Oracle高效算法。
We study an online classification problem with partial feedback in which individuals arrive one at a time from a fixed but unknown distribution, and must be classified as positive or negative. Our algorithm only observes the true label of an individual if they are given a positive classification. This setting captures many classification problems for which fairness is a concern: for example, in criminal recidivism prediction, recidivism is only observed if the inmate is released; in lending applications, loan repayment is only observed if the loan is granted. We require that our algorithms satisfy common statistical fairness constraints (such as equalizing false positive or negative rates -- introduced as "equal opportunity" in Hardt et al. (2016)) at every round, with respect to the underlying distribution. We give upper and lower bounds characterizing the cost of this constraint in terms of the regret rate (and show that it is mild), and give an oracle efficient algorithm that achieves the upper bound.
预测警务中失控的反馈循环
DOI：
--
发表时间：
2018
期刊：
and Transparency
影响因子：
--
作者：
Ensign, Danielle;Friedler, Sorelle A.;Neville, Scott;Scheidegger, Carlos;Venkatasubramanian, Suresh
通讯作者：
Venkatasubramanian, Suresh