公平的机器学习努力,以防止在社会中嵌入的机器学习应用程序中引起不公平。尽管公平和拟议的“公平算法”有各种各样的定义,但关于公平性仍然没有解决的概念问题。在本文中,我们认为随机性和公平性可以视为机器学习中的等效概念。我们通过吸引冯·米塞斯(Von Mises)的百年历史基础来获得相对的随机性概念,称为统计独立性。通过机器学习中的公平概念,也表示为统计独立性,然后我们将有关数据的随机性假设链接到公平预测的事后要求。这种联系证明了富有成果:我们用它来争辩说,随机性和公平本质上是相对的,随机性应反映其本质作为机器学习中的建模假设。
translated by 谷歌翻译
机器学习通常以经典的概率理论为前提,这意味着聚集是基于期望的。现在有多种原因可以激励人们将经典概率理论作为机器学习的数学基础。我们系统地检查了一系列强大而丰富的此类替代品,即各种称为光谱风险度量,Choquet积分或Lorentz规范。我们提出了一系列的表征结果,并演示了使这个光谱家族如此特别的原因。在此过程中,我们证明了所有连贯的风险度量的自然分层,从它们通过利用重新安排不变性Banach空间理论的结果来诱导的上层概率。我们凭经验证明了这种新的不确定性方法如何有助于解决实用的机器学习问题。
translated by 谷歌翻译
基于AI和机器学习的决策系统已在各种现实世界中都使用,包括医疗保健,执法,教育和金融。不再是牵强的,即设想一个未来,自治系统将推动整个业务决策,并且更广泛地支持大规模决策基础设施以解决社会最具挑战性的问题。当人类做出决定时,不公平和歧视的问题普遍存在,并且当使用几乎没有透明度,问责制和公平性的机器做出决定时(或可能会放大)。在本文中,我们介绍了\ textit {Causal公平分析}的框架,目的是填补此差距,即理解,建模,并可能解决决策设置中的公平性问题。我们方法的主要见解是将观察到数据中存在的差异的量化与基本且通常是未观察到的因果机制收集的因果机制的收集,这些机制首先会产生差异,挑战我们称之为因果公平的基本问题分析(FPCFA)。为了解决FPCFA,我们研究了分解差异和公平性的经验度量的问题,将这种变化归因于结构机制和人群的不同单位。我们的努力最终达到了公平地图,这是组织和解释文献中不同标准之间关系的首次系统尝试。最后,我们研究了进行因果公平分析并提出一本公平食谱的最低因果假设,该假设使数据科学家能够评估不同影响和不同治疗的存在。
translated by 谷歌翻译
近年来,解决机器学习公平性(ML)和自动决策的问题引起了处理人工智能的科学社区的大量关注。已经提出了ML中的公平定义的一种不同的定义,认为不同概念是影响人口中个人的“公平决定”的不同概念。这些概念之间的精确差异,含义和“正交性”尚未在文献中完全分析。在这项工作中,我们试图在这个解释中汲取一些订单。
translated by 谷歌翻译
Virtually all machine learning tasks are characterized using some form of loss function, and "good performance" is typically stated in terms of a sufficiently small average loss, taken over the random draw of test data. While optimizing for performance on average is intuitive, convenient to analyze in theory, and easy to implement in practice, such a choice brings about trade-offs. In this work, we survey and introduce a wide variety of non-traditional criteria used to design and evaluate machine learning algorithms, place the classical paradigm within the proper historical context, and propose a view of learning problems which emphasizes the question of "what makes for a desirable loss distribution?" in place of tacit use of the expected loss.
translated by 谷歌翻译
This review presents empirical researchers with recent advances in causal inference, and stresses the paradigmatic shifts that must be undertaken in moving from traditional statistical analysis to causal analysis of multivariate data. Special emphasis is placed on the assumptions that underly all causal inferences, the languages used in formulating those assumptions, the conditional nature of all causal and counterfactual claims, and the methods that have been developed for the assessment of such claims. These advances are illustrated using a general theory of causation based on the Structural Causal Model (SCM) described in Pearl (2000a), which subsumes and unifies other approaches to causation, and provides a coherent mathematical foundation for the analysis of causes and counterfactuals. In particular, the paper surveys the development of mathematical tools for inferring (from a combination of data and assumptions) answers to three types of causal queries: (1) queries about the effects of potential interventions, (also called "causal effects" or "policy evaluation") (2) queries about probabilities of counterfactuals, (including assessment of "regret," "attribution" or "causes of effects") and (3) queries about direct and indirect effects (also known as "mediation"). Finally, the paper defines the formal and conceptual relationships between the structural and potential-outcome frameworks and presents tools for a symbiotic analysis that uses the strong features of both.
translated by 谷歌翻译
算法公平吸引了机器学习社区越来越多的关注。文献中提出了各种定义,但是它们之间的差异和联系并未清楚地解决。在本文中,我们回顾并反思了机器学习文献中先前提出的各种公平概念,并试图与道德和政治哲学,尤其是正义理论的论点建立联系。我们还从动态的角度考虑了公平的询问,并进一步考虑了当前预测和决策引起的长期影响。鉴于特征公平性的差异,我们提出了一个流程图,该流程图包括对数据生成过程,预测结果和诱导的影响的不同类型的公平询问的隐式假设和预期结果。本文展示了与任务相匹配的重要性(人们希望执行哪种公平性)和实现预期目的的手段(公平分析的范围是什么,什么是适当的分析计划)。
translated by 谷歌翻译
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it is the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school. * Equal contribution. This work was done while JL was a Research Fellow at the Alan Turing Institute. 2 https://obamawhitehouse.archives.gov/blog/2016/05/04/big-risks-big-opportunities-intersection-big-dataand-civil-rights 31st Conference on Neural Information Processing Systems (NIPS 2017),
translated by 谷歌翻译
最近提出了可取分的关节移位作为一种数据集移位,可以从观察到的数据中估算特征。对于多项式(多级)分类设置,我们得出了可分解的关节变化在源(训练)分布,目标(测试)先前的类概率和特征的目标边缘分布方面的表示。在此结果的基础上,我们提出了联合重要性对齐的替代方案,同时指出了假设可分解的关节转移时遇到的局限性。本文的其他结果包括在一般数据集偏移和可分解关节转移下的后类概率的校正公式。此外,我们研究了假设可因素转移对样品选择引起的偏差的后果。
translated by 谷歌翻译
The notion of uncertainty is of major importance in machine learning and constitutes a key element of machine learning methodology. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions. Yet, due to the steadily increasing relevance of machine learning for practical applications and related issues such as safety requirements, new problems and challenges have recently been identified by machine learning scholars, and these problems may call for new methodological developments. In particular, this includes the importance of distinguishing between (at least) two different types of uncertainty, often referred to as aleatoric and epistemic. In this paper, we provide an introduction to the topic of uncertainty in machine learning as well as an overview of attempts so far at handling uncertainty in general and formalizing this distinction in particular.
translated by 谷歌翻译
我们建议出现的定量和客观概念。我们的建议使用算法信息理论作为一个客观框架的基础,其中某个字符串编码观测数据。这种字符串的Kolmogorov结构功能中有多个滴剂被视为出现的标志。我们的定义除了扩展了粗粒和边界条件的概念外,还提供了一些理论上的结果。最后,我们面对对动态系统和热力学的应用。
translated by 谷歌翻译
现有的制定公平计算定义的努力主要集中在平等的分布概念上,在这种情况下,平等是由系统中给出的资源或决策定义的。然而,现有的歧视和不公正通常是社会关系不平等的结果,而不是资源分配不平等。在这里,我们展示了对公平和平等的现有计算和经济定义的优化,无法防止不平等的社会关系。为此,我们提供了一个在简单的招聘市场中具有自我融合平衡的示例,该市场在关系上不平等,但满足了现有的公平分布概念。在此过程中,我们引入了公然的关系不公平的概念,对完整信息游戏进行了讨论,并讨论了该定义如何有助于启动一种将关系平等纳入计算系统的新方法。
translated by 谷歌翻译
最近的工作突出了因果关系在设计公平决策算法中的作用。但是,尚不清楚现有的公平因果概念如何相互关系,或者将这些定义作为设计原则的后果是什么。在这里,我们首先将算法公平性的流行因果定义组装成两个广泛的家庭:(1)那些限制决策对反事实差异的影响的家庭; (2)那些限制了法律保护特征(如种族和性别)对决策的影响。然后,我们在分析和经验上表明,两个定义的家庭\ emph {几乎总是总是} - 从一种理论意义上讲 - 导致帕累托占主导地位的决策政策,这意味着每个利益相关者都有一个偏爱的替代性,不受限制的政策从大型自然级别中绘制。例如,在大学录取决定的情况下,每位利益相关者都不支持任何对学术准备和多样性的中立或积极偏好的利益相关者,将不利于因果公平定义的政策。的确,在因果公平的明显定义下,我们证明了由此产生的政策要求承认所有具有相同概率的学生,无论学术资格或小组成员身份如何。我们的结果突出了正式的局限性和因果公平的常见数学观念的潜在不利后果。
translated by 谷歌翻译
Recommender systems can strongly influence which information we see online, e.g., on social media, and thus impact our beliefs, decisions, and actions. At the same time, these systems can create substantial business value for different stakeholders. Given the growing potential impact of such AI-based systems on individuals, organizations, and society, questions of fairness have gained increased attention in recent years. However, research on fairness in recommender systems is still a developing area. In this survey, we first review the fundamental concepts and notions of fairness that were put forward in the area in the recent past. Afterward, through a review of more than 150 scholarly publications, we present an overview of how research in this field is currently operationalized, e.g., in terms of general research methodology, fairness measures, and algorithmic approaches. Overall, our analysis of recent works points to specific research gaps. In particular, we find that in many research works in computer science, very abstract problem operationalizations are prevalent, and questions of the underlying normative claims and what represents a fair recommendation in the context of a given application are often not discussed in depth. These observations call for more interdisciplinary research to address fairness in recommendation in a more comprehensive and impactful manner.
translated by 谷歌翻译
因果关系是理解世界的科学努力的基本组成部分。不幸的是,在心理学和社会科学中,因果关系仍然是禁忌。由于越来越多的建议采用因果方法进行研究的重要性,我们重新制定了心理学研究方法的典型方法,以使不可避免的因果理论与其余的研究渠道协调。我们提出了一个新的过程,该过程始于从因果发现和机器学习的融合中纳入技术的发展,验证和透明的理论形式规范。然后,我们提出将完全指定的理论模型的复杂性降低到与给定目标假设相关的基本子模型中的方法。从这里,我们确定利息量是否可以从数据中估算出来,如果是的,则建议使用半参数机器学习方法来估计因果关系。总体目标是介绍新的研究管道,该管道可以(a)促进与测试因果理论的愿望兼容的科学询问(b)鼓励我们的理论透明代表作为明确的数学对象,(c)将我们的统计模型绑定到我们的统计模型中该理论的特定属性,因此减少了理论到模型间隙通常引起的规范不足问题,以及(d)产生因果关系和可重复性的结果和估计。通过具有现实世界数据的教学示例来证明该过程,我们以摘要和讨论来结论。
translated by 谷歌翻译
尽管在机器学习的方法论核心中是一个问题,但如何比较分类器仍未达成一致的共识。每个比较框架都面临着(至少)三个基本挑战:质量标准的多样性,数据集的多样性以及选择数据集选择的随机性/任意性。在本文中,我们通过采用决策理论的最新发展,为生动的辩论增添了新的观点。我们最终的框架基于所谓的偏好系统,通过广义的随机优势概念对分类器进行排名,该概念强大地绕过了繁琐的,甚至通常是自相矛盾的,对聚合的依赖。此外,我们表明,可以通过解决易于手柄的线性程序和通过适应的两样本观察随机化测试进行统计测试来实现广泛的随机优势。这确实产生了一个有力的框架,可以同时相对于多个质量标准进行分类器的统计比较。我们在模拟研究和标准基准数据集中说明和研究我们的框架。
translated by 谷歌翻译
每个已知的人工深神经网络(DNN)都对应于规范Grothendieck的拓扑中的一个物体。它的学习动态对应于此拓扑中的形态流动。层中的不变结构(例如CNNS或LSTMS)对应于Giraud的堆栈。这种不变性应该是对概括属性的原因,即从约束下的学习数据中推断出来。纤维代表语义前类别(Culioli,Thom),在该类别上定义了人工语言,内部逻辑,直觉主义者,古典或线性(Girard)。网络的语义功能是其能够用这种语言表达理论的能力,以回答输出数据中有关输出的问题。语义信息的数量和空间是通过类比与2015年香农和D.Bennequin的Shannon熵的同源解释来定义的。他们概括了Carnap和Bar-Hillel(1952)发现的措施。令人惊讶的是,上述语义结构通过封闭模型类别的几何纤维对象进行了分类,然后它们产生了DNNS及其语义功能的同位不变。故意类型的理论(Martin-Loef)组织了这些物体和它们之间的纤维。 Grothendieck的导数分析了信息内容和交流。
translated by 谷歌翻译
In this paper, we provide a theoretical framework to analyze an agent who misinterprets or misperceives the true decision problem she faces. Within this framework, we show that a wide range of behavior observed in experimental settings manifest as failures to perceive implications, in other words, to properly account for the logical relationships between various payoff relevant contingencies. We present behavioral characterizations corresponding to several benchmarks of logical sophistication and show how it is possible to identify which implications the agent fails to perceive. Thus, our framework delivers both a methodology for assessing an agent's level of contingent thinking and a strategy for identifying her beliefs in the absence full rationality.
translated by 谷歌翻译
在这项工作中,我们对基本思想和新颖的发展进行了综述的综述,这是基于最小的假设的一种无创新的,无分配的,非参数预测的方法 - 能够以非常简单的方式预测集屈服在有限样本案例中,在统计意义上也有效。论文中提供的深入讨论涵盖了共形预测的理论基础,然后继续列出原始想法的更高级的发展和改编。
translated by 谷歌翻译
团体公平指标是评估基于预测决策系统公平性的既定方法。但是,这些指标仍然与哲学理论相关,其道德含义通常不清楚。我们提出了一个一般框架,用于分析基于分配正义理论的决策系统的公平性,包括与不同规范立场相对应的不同既定的“正义模式”。我们表明,最受欢迎的集体公平度量指标可以解释为我们方法的特殊情况。因此,我们为群体公平指标提供了一个统一和解释的框架,该框架揭示了与它们相关的规范性选择,并允许理解其道德实质。同时,我们提供了可能公平指标的延伸空间,而不是公平ML文献中当前讨论的指标。我们的框架还允许克服几个群体公平指标的局限性,这些指标在文献中受到批评,最著名的是(1)它们是基于平等的,即他们要求群体之间的某种形式的平等性,这有时可能有害于边缘化。组,(2)他们仅比较跨群体的决策,但对这些群体的后果没有比较,并且(3)分配正义文献的全部广度不足。
translated by 谷歌翻译