Fair Machine Learning endeavors to prevent unfairness arising in the context of machine learning applications embedded in society. Despite the variety of definitions of fairness and proposed "fair algorithms", there remain unresolved conceptual problems regarding fairness. In this paper, we dissect the role of statistical independence in fairness and randomness notions regularly used in machine learning. Thereby, we are led to a suprising hypothesis: randomness and fairness can be considered equivalent concepts in machine learning. In particular, we obtain a relativized notion of randomness expressed as statistical independence by appealing to Von Mises' century-old foundations for probability. This notion turns out to be "orthogonal" in an abstract sense to the commonly used i.i.d.-randomness. Using standard fairness notions in machine learning, which are defined via statistical independence, we then link the ex ante randomness assumptions about the data to the ex post requirements for fair predictions. This connection proves fruitful: we use it to argue that randomness and fairness are essentially relative and that both concepts should reflect their nature as modeling assumptions in machine learning.
翻译:公平机器学习(Fair Machine Learning) 努力防止社会机器学习应用中产生的不公平现象。 尽管对公平的定义和拟议的“公平算法”有各种各样的定义, 关于公平的概念问题仍未解决。 在本文中,我们将统计独立的作用在公平性和随机性概念上与机器学习经常使用的概念分开。 因此,我们被引向一个令人怀疑的假设:随机性和公平可以被视为机器学习中的等同概念。 特别是,我们获得了一种相对的随机性概念,它表现为统计独立,它吸引了冯·米塞斯百年久久以来的概率基础。 这个概念在抽象意义上与常用的i. i. d.- randomness(i. d.-randomness)是“ortogonal ” 概念。 在机器学习中使用标准的公平概念(通过统计独立定义),我们随后将数据假设与事后的公平预测要求联系起来。 这个联系是富有成效的:我们用它来论证随机性和公平性基本上是相对的, 并且这两个概念应该反映机器学习中的模拟假设的性质。