Calibration for the (Computationally-Identifiable) Masses
Calibration for the (Computationally-Identifiable) Masses
复制标题
（计算可识别）质量的校准
DOI：
10.1038/362400b0
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
G. Rothblum
中科院分区：
文献类型：
--
作者：
Úrsula Hébert;Michael P. Kim;Omer Reingold;G. Rothblum
随着算法越来越多地为个人做出的决策提供了信息，解决这些算法可能具有歧视性的担忧变得越来越重要。由于许多原因，算法的输出可以具有歧视性，最值得注意的是：（1）用于训练该算法的数据可能会偏向（以各种方式），以偏爱某些人群而不是其他人群； （2）对该培训数据的分析可能会无意中或恶意地引入数据中没有出现的偏见。这项工作着重于后一种关注。
我们开发和研究多核酸 - 算法公平性的新度量，旨在减轻对从数据学习预测指标进行歧视的担忧。多核算保证可以在指定的计算类别中识别的每个子群的准确（校准）预测。我们认为班级很富有。特别是，它可以包含受保护组的许多重叠子组。
我们表明，在许多情况下，这种强烈的保护侵害歧视的概念既可以达到和与获得准确的预测的目标。在此过程中，我们提出了用于学习多校准预测指标，研究该任务的计算复杂性的新算法，并将新的连接与计算学习模型（例如不可知论学习）建立了新的联系。
As algorithms increasingly inform and influence decisions made about individuals, it becomes increasingly important to address concerns that these algorithms might be discriminatory. The output of an algorithm can be discriminatory for many reasons, most notably: (1) the data used to train the algorithm might be biased (in various ways) to favor certain populations over others; (2) the analysis of this training data might inadvertently or maliciously introduce biases that are not borne out in the data. This work focuses on the latter concern.
We develop and study multicalbration -- a new measure of algorithmic fairness that aims to mitigate concerns about discrimination that is introduced in the process of learning a predictor from data. Multicalibration guarantees accurate (calibrated) predictions for every subpopulation that can be identified within a specified class of computations. We think of the class as being quite rich; in particular, it can contain many overlapping subgroups of a protected group.
We show that in many settings this strong notion of protection from discrimination is both attainable and aligned with the goal of obtaining accurate predictions. Along the way, we present new algorithms for learning a multicalibrated predictor, study the computational complexity of this task, and draw new connections to computational learning models such as agnostic learning.
通过计算限制的意识实现公平
DOI：
--
发表时间：
2018
期刊：
Neural Information Processing Systems (Nurips
影响因子：
--
作者：
Kim, Michael P.;Reingold, Omer;Rothblum, Guy N.
通讯作者：
Rothblum, Guy N.