在高赌注域中的机器学习工具的实际应用通常被调节为公平，因此预测目标应该满足相对于受保护属性的奇偶校验的一些定量概念。然而，公平性和准确性之间的确切权衡并不完全清楚，即使是对分类问题的基本范式也是如此。在本文中，我们通过在任何公平分类器的群体误差之和中提供较低的界限，在分类设置中表征统计奇偶校验和准确性之间的固有权衡。我们不可能的定理可以被解释为公平的某种不确定性原则：如果基本率不同，那么符合统计奇偶校验的任何公平分类器都必须在至少一个组中产生很大的错误。我们进一步扩展了这一结果，以便在学习公平陈述的角度下给出任何（大约）公平分类者的联合误差的下限。为了表明我们的下限是紧张的，假设Oracle访问贝叶斯（潜在不公平）分类器，我们还构造了一种返回一个随机分类器的算法，这是最佳和公平的。有趣的是，当受保护的属性可以采用超过两个值时，这个下限的扩展不承认分析解决方案。然而，在这种情况下，我们表明，通过解决线性程序，我们可以通过解决我们作为电视 - 重心问题的术语，电视距离的重心问题来有效地计算下限。在上面，我们证明，如果集团明智的贝叶斯最佳分类器是关闭的，那么学习公平的表示导致公平的替代概念，称为准确性奇偶校验，这使得错误率在组之间关闭。最后，我们还在现实世界数据集上进行实验，以确认我们的理论发现。

We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy.In line with other studies, our notion is oblivious: it depends only on the joint statistics of the predictor, the target and the protected attribute, but not on interpretation of individual features. We study the inherent limits of defining and identifying biases based on such oblivious measures, outlining what can and cannot be inferred from different oblivious tests.We illustrate our notion using a case study of FICO credit scores.

The most prevalent notions of fairness in machine learning are statistical definitions: they fix a small collection of high-level, pre-defined groups (such as race or gender), and then ask for approximate parity of some statistic of the classifier (like positive classification rate or false positive rate) across these groups. Constraints of this form are susceptible to (intentional or inadvertent) fairness gerrymandering, in which a classifier appears to be fair on each individual group, but badly violates the fairness constraint on one or more structured subgroups defined over the protected attributes (such as certain combinations of protected attribute values). We propose instead to demand statistical notions of fairness across exponentially (or infinitely) many subgroups, defined by a structured class of functions over the protected attributes. This interpolates between statistical definitions of fairness, and recently proposed individual notions of fairness, but it raises several computational challenges. It is no longer clear how to even check or audit a fixed classifier to see if it satisfies such a strong definition of fairness. We prove that the computational problem of auditing subgroup fairness for both equality of false positive rates and statistical parity is equivalent to the problem of weak agnostic learning -which means it is computationally hard in the worst case, even for simple structured subclasses. However, it also suggests that common heuristics for learning can be applied to successfully solve the auditing problem in practice.We then derive two algorithms that provably converge to the best fair distribution over classifiers in a given class, given access to oracles which can optimally solve the agnostic learning problem. The algorithms are based on a formulation of subgroup fairness as a two-player zero-sum game between a Learner (the primal player) and an Auditor (the dual player). Both algorithms compute an equilibrium of this game. We obtain our first algorithm by simulating play of the game by having Learner play an instance of the no-regret Follow the Perturbed Leader algorithm, and having Auditor play best response. This algorithm provably converges to an approximate Nash equilibrium (and thus to an approximately optimal subgroup-fair distribution over classifiers) in a polynomial number of steps. We obtain our second algorithm by simulating play of the game by having both players play Fictitious Play, which enjoys only provably asymptotic convergence, but has the merit of simplicity and faster per-step computation. We implement the Fictitious Play version using linear regression as a heuristic oracle, and show that we can effectively both audit and learn fair classifiers on real datasets.

Due to the ability of deep neural nets to learn rich representations, recent advances in unsupervised domain adaptation have focused on learning domain-invariant features that achieve a small error on the source domain. The hope is that the learnt representation, together with the hypothesis learnt from the source domain, can generalize to the target domain. In this paper, we first construct a simple counterexample showing that, contrary to common belief, the above conditions are not sufficient to guarantee successful domain adaptation. In particular, the counterexample exhibits conditional shift: the class-conditional distributions of input features change between source and target domains. To give a sufficient condition for domain adaptation, we propose a natural and interpretable generalization upper bound that explicitly takes into account the aforementioned shift. Moreover, we shed new light on the problem by proving an information-theoretic lower bound on the joint error of any domain adaptation method that attempts to learn invariant representations. Our result characterizes a fundamental tradeoff between learning invariant representations and achieving small joint error on both domains when the marginal label distributions differ from source to target. Finally, we conduct experiments on real-world datasets that corroborate our theoretical findings. We believe these insights are helpful in guiding the future design of domain adaptation and representation learning algorithms.

我们展示了如何采用回归函数$ \ hat {f} $，该{f} $适当地``多校准''并有效地将其后处理成近似错误的分类器，使分类器满足各种公平限制。后处理不需要标记的数据，只有一定数量的未标记数据和计算。计算$ \ hat f $的计算和样本复杂性要求与解决单个公平学习任务的要求相媲美，但实际上可以用来有效地解决许多不同的下游公平约束的学习问题。我们的后处理方法可以轻松处理相交组，从而将先前的工作推广到后处理回归功能上，以满足仅应用于分离组的公平约束。我们的工作扩展了最近的工作，表明多校准的回归函数是``omnipredictors''（即可以在后处理以最佳解决无约束的ERM问题）以进行约束优化。

我们在禁用的对手存在下研究公平分类，允许获得$ \ eta $，选择培训样本的任意$ \ eta $ -flaction，并任意扰乱受保护的属性。由于战略误报，恶意演员或归责的错误，受保护属性可能不正确的设定。和现有的方法，使随机或独立假设对错误可能不满足其在这种对抗环境中的保证。我们的主要贡献是在这种对抗的环境中学习公平分类器的优化框架，这些普遍存在的准确性和公平性提供了可证明的保证。我们的框架适用于多个和非二进制保护属性，专为大类线性分数公平度量设计，并且还可以处理除了受保护的属性之外的扰动。我们证明了我们框架的近密性，对自然假设类别的保证：没有算法可以具有明显更好的准确性，并且任何具有更好公平性的算法必须具有较低的准确性。凭经验，我们评估了我们对统计率的统计税务统计税率为一个对手的统计税率产生的分类机。

随着算法治理的快速发展，公平性已成为机器学习模型的强制性属性，以抑制无意的歧视。在本文中，我们着重于实现公平性的预处理方面，并提出了一种数据重新拨打的方法，该方法仅在培训阶段调整样本的重量。与通常为每个（子）组分配均匀权重的大多数以前的重新校正方法不同，我们对每个训练样本在与公平相关的数量和预测效用方面的影响进行颗粒片，并根据在从影响下的影响下对单个权重进行计算。公平和效用。实验结果表明，以前的方法以不可忽略的实用性成本达到公平性，而为了取得重大优势，我们的方法可以从经验上释放权衡并获得无需成本的公平就可以平等机会。与多个现实世界表格数据集中的基线方法相比，我们通过香草分类器和标准培训过程证明了通过香草分类器和标准培训过程的公平性。可在https://github.com/brandeis-machine-learning/influence-fairness上获得代码。

Omnipredictors（Gopalan，Kalai，Reingold，Sharan和Wieder ITCS 2021）的概念提出了一种新的损失最小化范式。与损失损失$ c $相比，无需基于已知的损失功能学习预测指标，而是可以轻松地进行后处理以最大程度地减少任何丰富的损失功能家族。已经表明，这种杂手已经存在，并暗示（对于所有凸和Lipschitz损失函数），通过算法公平文献的多核概念的概念。然而，通常情况下，所选的动作必须遵守一些其他约束（例如能力或奇偶校验约束）。总体而言，全能器的原始概念并不适用于这种良好动机和大量研究的损失最小化的背景。在本文中，我们介绍了综合器，以进行约束优化并研究其复杂性和含义。我们介绍的概念使学习者不知道后来将分配的损失函数以及后来将施加的约束，只要已知用于定义这些约束的亚群的范围。该论文显示了如何依靠适当的多核变体获得限制优化问题的全能器。对于一些有趣的约束和一般损失函数以及一般约束和一些有趣的损失函数，我们显示了如何通过多核的变体隐含的，该变体的复杂性与标准的多核电相似。我们证明，在一般情况下，标准的数学启动不足，表明全能器是通过相对于包含$ c $中所有级别假设集的类的多核算来暗示的。我们还研究了约束是群体公平概念时的含义。

公司跨行业对机器学习（ML）的快速传播采用了重大的监管挑战。一个这样的挑战就是可伸缩性：监管机构如何有效地审核这些ML模型，以确保它们是公平的？在本文中，我们启动基于查询的审计算法的研究，这些算法可以以查询有效的方式估算ML模型的人口统计学率。我们提出了一种最佳的确定性算法，以及具有可比保证的实用随机，甲骨文效率的算法。此外，我们进一步了解了随机活动公平估计算法的最佳查询复杂性。我们对主动公平估计的首次探索旨在将AI治理置于更坚定的理论基础上。

这项工作提供了在人口统计学限制下的最佳分类函数的几种基本特征。在意识框架中，类似于经典的不受限制的分类案例，我们表明，在这种公平性约束下，最大化准确性等于解决相应的回归问题，然后在级别$ 1/2 $上进行阈值。我们将此结果扩展到线性分类分类度量（例如，$ {\ rm f} $ - 得分，AM度量，平衡准确性等），突出了回归问题在此框架中所起的基本作用。我们的结果利用了最近在人口统计学限制与多界限最佳运输公式之间建立了联系。从非正式的角度来看，我们的结果表明，通过解决公平回归问题的解决方案来代替标签的有条件期望，可以实现无约束的问题与公平问题之间的过渡。最后，利用我们的分析，我们证明了在两个敏感群体的情况下，意识和不认识的设置之间的等效性。

尽管大规模的经验风险最小化（ERM）在各种机器学习任务中取得了高精度，但公平的ERM受到公平限制与随机优化的不兼容的阻碍。我们考虑具有离散敏感属性以及可能需要随机求解器的可能性大型模型和数据集的公平分类问题。现有的内部处理公平算法在大规模设置中要么是不切实际的，因为它们需要在每次迭代时进行大量数据，要么不保证它们会收敛。在本文中，我们开发了第一个具有保证收敛性的随机内处理公平算法。对于人口统计学，均衡的赔率和公平的机会均等的概念，我们提供了算法的略有变化，称为Fermi，并证明这些变化中的每一个都以任何批次大小收敛于随机优化。从经验上讲，我们表明Fermi适合具有多个（非二进制）敏感属性和非二进制目标的随机求解器，即使Minibatch大小也很小，也可以很好地表现。广泛的实验表明，与最先进的基准相比，FERMI实现了所有经过测试的设置之间的公平违规和测试准确性之间最有利的权衡，该基准是人口统计学奇偶校验，均衡的赔率，均等机会，均等机会。这些好处在小批量的大小和非二元分类具有大量敏感属性的情况下尤其重要，这使得费米成为大规模问题的实用公平算法。

解决机器学习模型的公平关注是朝着实际采用现实世界自动化系统中的至关重要的一步。尽管已经开发了许多方法来从数据培训公平模型，但对这些方法对数据损坏的鲁棒性知之甚少。在这项工作中，我们考虑在最坏情况下的数据操作下进行公平意识学习。我们表明，在某些情况下，对手可能会迫使任何学习者返回过度偏见的分类器，无论样本量如何，有或没有降解的准确性，并且多余的偏见的强度会增加数据中数据不足的受保护组的学习问题，而数据中有代表性不足的组。我们还证明，我们的硬度结果紧密到不断的因素。为此，我们研究了两种自然学习算法，以优化准确性和公平性，并表明这些算法在损坏比和较大数据限制中受保护的群体频率方面享有订单最佳的保证。

机器学习中的歧视通常沿多个维度（又称保护属性）出现；因此，希望确保\ emph {交叉公平} - 即，没有任何子组受到歧视。众所周知，确保\ emph {边际公平}对于每个维度而言，独立不够。但是，由于亚组的指数数量，直接测量数据交叉公平性是不可能的。在本文中，我们的主要目标是通过统计分析详细了解边际和交叉公平之间的关系。我们首先确定一组足够的条件，在这些条件下可以获得确切的关系。然后，在一般情况下，我们证明了相交公平性的高概率的界限（通过边际公平和其他有意义的统计量很容易计算）。除了它们的描述价值之外，我们还可以利用这些理论界限来得出一种启发式，从而通过以相关的方式选择了我们描述相交子组的保护属性来改善交叉公平的近似和边界。最后，我们测试了实际和合成数据集的近似值和界限的性能。

We study fairness in classification, where individuals are classified, e.g., admitted to a university, and the goal is to prevent discrimination against individuals based on their membership in some group, while maintaining utility for the classifier (the university). The main conceptual contribution of this paper is a framework for fair classification comprising (1) a (hypothetical) task-specific metric for determining the degree to which individuals are similar with respect to the classification task at hand; (2) an algorithm for maximizing utility subject to the fairness constraint, that similar individuals are treated similarly. We also present an adaptation of our approach to achieve the complementary goal of "fair affirmative action," which guarantees statistical parity (i.e., the demographics of the set of individuals receiving any classification are the same as the demographics of the underlying population), while treating similar individuals as similarly as possible. Finally, we discuss the relationship of fairness to privacy: when fairness implies privacy, and how tools developed in the context of differential privacy may be applied to fairness.

We present a systematic approach for achieving fairness in a binary classification setting. While we focus on two well-known quantitative definitions of fairness, our approach encompasses many other previously studied definitions as special cases. The key idea is to reduce fair classification to a sequence of cost-sensitive classification problems, whose solutions yield a randomized classifier with the lowest (empirical) error subject to the desired constraints. We introduce two reductions that work for any representation of the cost-sensitive classifier and compare favorably to prior baselines on a variety of data sets, while overcoming several of their disadvantages.

我们考虑为多类分类任务生产公平概率分类器的问题。我们以“投射”预先培训（且可能不公平的）分类器在满足目标群体对要求的一组模型上的“投影”来提出这个问题。新的投影模型是通过通过乘法因子后处理预训练的分类器的输出来给出的。我们提供了一种可行的迭代算法，用于计算投影分类器并得出样本复杂性和收敛保证。与最先进的基准测试的全面数值比较表明，我们的方法在准确性权衡曲线方面保持了竞争性能，同时在大型数据集中达到了有利的运行时。我们还在具有多个类别，多个相互保护组和超过1M样本的开放数据集上评估了我们的方法。

Algorithmic fairness is becoming increasingly important in data mining and machine learning. Among others, a foundational notation is group fairness. The vast majority of the existing works on group fairness, with a few exceptions, primarily focus on debiasing with respect to a single sensitive attribute, despite the fact that the co-existence of multiple sensitive attributes (e.g., gender, race, marital status, etc.) in the real-world is commonplace. As such, methods that can ensure a fair learning outcome with respect to all sensitive attributes of concern simultaneously need to be developed. In this paper, we study the problem of information-theoretic intersectional fairness (InfoFair), where statistical parity, a representative group fairness measure, is guaranteed among demographic groups formed by multiple sensitive attributes of interest. We formulate it as a mutual information minimization problem and propose a generic end-to-end algorithmic framework to solve it. The key idea is to leverage a variational representation of mutual information, which considers the variational distribution between learning outcomes and sensitive attributes, as well as the density ratio between the variational and the original distributions. Our proposed framework is generalizable to many different settings, including other statistical notions of fairness, and could handle any type of learning task equipped with a gradient-based optimizer. Empirical evaluations in the fair classification task on three real-world datasets demonstrate that our proposed framework can effectively debias the classification results with minimal impact to the classification accuracy.

We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenario where the data contains multiple or even many subgroups, each with limited number of samples. As a result, we present a principled method for learning a fair predictor for all subgroups via formulating it as a bilevel objective. Specifically, the subgroup specific predictors are learned in the lower-level through a small amount of data and the fair predictor. In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors. We further prove that such a bilevel objective can effectively control the group sufficiency and generalization error. We evaluate the proposed framework on real-world datasets. Empirical evidence suggests the consistently improved fair predictions, as well as the comparable accuracy to the baselines.

Given an algorithmic predictor that is "fair" on some source distribution, will it still be fair on an unknown target distribution that differs from the source within some bound? In this paper, we study the transferability of statistical group fairness for machine learning predictors (i.e., classifiers or regressors) subject to bounded distribution shifts. Such shifts may be introduced by initial training data uncertainties, user adaptation to a deployed predictor, dynamic environments, or the use of pre-trained models in new settings. Herein, we develop a bound that characterizes such transferability, flagging potentially inappropriate deployments of machine learning for socially consequential tasks. We first develop a framework for bounding violations of statistical fairness subject to distribution shift, formulating a generic upper bound for transferred fairness violations as our primary result. We then develop bounds for specific worked examples, focusing on two commonly used fairness definitions (i.e., demographic parity and equalized odds) and two classes of distribution shift (i.e., covariate shift and label shift). Finally, we compare our theoretical bounds to deterministic models of distribution shift and against real-world data, finding that we are able to estimate fairness violation bounds in practice, even when simplifying assumptions are only approximately satisfied.

Algorithmic fairness plays an increasingly critical role in machine learning research. Several group fairness notions and algorithms have been proposed. However, the fairness guarantee of existing fair classification methods mainly depends on specific data distributional assumptions, often requiring large sample sizes, and fairness could be violated when there is a modest number of samples, which is often the case in practice. In this paper, we propose FaiREE, a fair classification algorithm that can satisfy group fairness constraints with finite-sample and distribution-free theoretical guarantees. FaiREE can be adapted to satisfy various group fairness notions (e.g., Equality of Opportunity, Equalized Odds, Demographic Parity, etc.) and achieve the optimal accuracy. These theoretical guarantees are further supported by experiments on both synthetic and real data. FaiREE is shown to have favorable performance over state-of-the-art algorithms.