我们提出了简单的主动采样和重新重量策略,以优化最小最大公平性,可以应用于通过损耗最小化学习的任何分类或回归模型。我们的方法背后的关键直觉是在每个TIMESTEP中使用来自当前模型中最差的组的DataPoint,以更新模型。实施的易于实现和我们稳健的制定的一般性使其成为提高糟糕表现群体的模型性能的有吸引力的选择。对于凸起的学习问题,如线性或逻辑回归,我们提供了对我们的策略的细粒度分析,证明了其收敛速度对Min-Max Fair解决方案。
translated by 谷歌翻译
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。
translated by 谷歌翻译
Distributionally robust optimization (DRO) can improve the robustness and fairness of learning methods. In this paper, we devise stochastic algorithms for a class of DRO problems including group DRO, subpopulation fairness, and empirical conditional value at risk (CVaR) optimization. Our new algorithms achieve faster convergence rates than existing algorithms for multiple DRO settings. We also provide a new information-theoretic lower bound that implies our bounds are tight for group DRO. Empirically, too, our algorithms outperform known methods
translated by 谷歌翻译
在联邦学习中,对受保护群体的公平预测是许多应用程序的重要限制。不幸的是,先前研究集团联邦学习的工作往往缺乏正式的融合或公平保证。在这项工作中,我们为可证明的公平联合学习提供了一个一般框架。特别是,我们探索并扩展了有限的群体损失的概念,作为理论上的群体公平方法。使用此设置,我们提出了一种可扩展的联合优化方法,该方法在许多群体公平限制下优化了经验风险。我们为该方法提供收敛保证,并为最终解决方案提供公平保证。从经验上讲,我们评估了公平ML和联合学习的共同基准的方法,表明它可以比基线方法提供更公平,更准确的预测。
translated by 谷歌翻译
我们展示了一个联合学习框架,旨在强大地提供具有异构数据的各个客户端的良好预测性能。所提出的方法对基于SuperQualile的学习目标铰接,捕获异构客户端的误差分布的尾统计。我们提出了一种随机训练算法,其与联合平均步骤交织差异私人客户重新重量步骤。该提出的算法支持有限时间收敛保证,保证覆盖凸和非凸面设置。关于联邦学习的基准数据集的实验结果表明,我们的方法在平均误差方面与古典误差竞争,并且在误差的尾统计方面优于它们。
translated by 谷歌翻译
A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. We argue that, with the existing training and inference, federated models can be biased towards different clients. Instead, we propose a new framework of agnostic federated learning, where the centralized model is optimized for any target distribution formed by a mixture of the client distributions. We further show that this framework naturally yields a notion of fairness. We present data-dependent Rademacher complexity guarantees for learning with this objective, which guide the definition of an algorithm for agnostic federated learning. We also give a fast stochastic optimization algorithm for solving the corresponding optimization problem, for which we prove convergence bounds, assuming a convex loss function and hypothesis set. We further empirically demonstrate the benefits of our approach in several datasets. Beyond federated learning, our framework and algorithm can be of interest to other learning scenarios such as cloud computing, domain adaptation, drifting, and other contexts where the training and test distributions do not coincide. MotivationA key learning scenario in large-scale applications is that of federated learning. In that scenario, a centralized model is trained based on data originating from a large number of clients, which may be mobile phones, other mobile devices, or sensors (Konečnỳ, McMahan, Yu, Richtárik, Suresh, and Bacon, 2016b;Konečnỳ, McMahan, Ramage, and Richtárik, 2016a). The training data typically remains distributed over the clients, each with possibly unreliable or relatively slow network connections.Federated learning raises several types of issues and has been the topic of multiple research efforts. These include systems, networking and communication bottleneck problems due to frequent exchanges between the central server and the clients . To deal with such problems, suggested an averaging technique that consists of transmitting the central model to a subset of clients, training it with the data locally available, and averaging the local updates. Smith et al. (2017) proposed to further leverage the relationship between clients, assumed to be known, and cast
translated by 谷歌翻译
Spectral risk objectives - also called $L$-risks - allow for learning systems to interpolate between optimizing average-case performance (as in empirical risk minimization) and worst-case performance on a task. We develop stochastic algorithms to optimize these quantities by characterizing their subdifferential and addressing challenges such as biasedness of subgradient estimates and non-smoothness of the objective. We show theoretically and experimentally that out-of-the-box approaches such as stochastic subgradient and dual averaging are hindered by bias and that our approach outperforms them.
translated by 谷歌翻译
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.
translated by 谷歌翻译
公平的机器学习研究人员(ML)围绕几个公平标准结合,这些标准为ML模型公平提供了正式的定义。但是,这些标准有一些严重的局限性。我们确定了这些正式公平标准的四个主要缺点,并旨在通过扩展性能预测以包含分配强大的目标来帮助解决这些问题。
translated by 谷歌翻译
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。
translated by 谷歌翻译
尽管学习已成为现代信息处理的核心组成部分,但现在有足够的证据表明它可以导致偏见,不安全和有偏见的系统。因此,对学习要求施加要求至关重要,尤其是在达到社会,工业和医疗领域的关键应用程序时。但是,大多数现代统计问题的非跨性别性只有通过限制引入而加剧。尽管通常可以使用经验风险最小化来学习良好的无约束解决方案,即使获得满足统计约束的模型也可能具有挑战性。更重要的是,一个好。在本文中,我们通过在经验双重领域中学习来克服这个问题,在经验的双重领域中,统计学上的统计学习问题变得不受限制和确定性。我们通过界定经验二元性差距来分析这种方法的概括特性 - 即,我们的近似,可拖动解决方案与原始(非凸)统计问题的解决方案之间的差异 - 并提供实用的约束学习算法。这些结果建立了与经典学习理论的约束,从而可以明确地在学习中使用约束。我们说明了这种理论和算法受到速率受限的学习应用,这是在公平和对抗性鲁棒性中产生的。
translated by 谷歌翻译
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。
translated by 谷歌翻译
We initiate a formal study of reproducibility in optimization. We define a quantitative measure of reproducibility of optimization procedures in the face of noisy or error-prone operations such as inexact or stochastic gradient computations or inexact initialization. We then analyze several convex optimization settings of interest such as smooth, non-smooth, and strongly-convex objective functions and establish tight bounds on the limits of reproducibility in each setting. Our analysis reveals a fundamental trade-off between computation and reproducibility: more computation is necessary (and sufficient) for better reproducibility.
translated by 谷歌翻译
在结果决策中使用机器学习模型通常会加剧社会不平等,特别是对种族和性别定义的边缘化群体成员产生不同的影响。 ROC曲线(AUC)下的区域被广泛用于评估机器学习中评分功能的性能,但与其他性能指标相比,在算法公平性中进行了研究。由于AUC的成对性质,定义基于AUC的组公平度量是成对依赖性的,并且可能涉及\ emph {group}和\ emph {group} aucs。重要的是,仅考虑一种AUC类别不足以减轻AUC优化的不公平性。在本文中,我们提出了一个最小值学习和偏置缓解框架,该框架既包含组内和组间AUC,同时保持实用性。基于这个Rawlsian框架,我们设计了一种有效的随机优化算法,并证明了其收敛到最小组级AUC。我们对合成数据集和现实数据集进行了数值实验,以验证Minimax框架的有效性和所提出的优化算法。
translated by 谷歌翻译
标签 - 不平衡和组敏感分类中的目标是优化相关的指标,例如平衡错误和相同的机会。经典方法,例如加权交叉熵,在训练深网络到训练(TPT)的终端阶段时,这是超越零训练误差的训练。这种观察发生了最近在促进少数群体更大边值的直观机制之后开发启发式替代品的动力。与之前的启发式相比,我们遵循原则性分析,说明不同的损失调整如何影响边距。首先,我们证明,对于在TPT中训练的所有线性分类器,有必要引入乘法,而不是添加性的Logit调整,以便对杂项边缘进行适当的变化。为了表明这一点,我们发现将乘法CE修改的连接到成本敏感的支持向量机。也许是违反,我们还发现,在培训开始时,相同的乘法权重实际上可以损害少数群体。因此,虽然在TPT中,添加剂调整无效,但我们表明它们可以通过对乘法重量的初始负效应进行抗衡来加速会聚。通过这些发现的动机,我们制定了矢量缩放(VS)丢失,即捕获现有技术作为特殊情况。此外,我们引入了对群体敏感分类的VS损失的自然延伸,从而以统一的方式处理两种常见类型的不平衡(标签/组)。重要的是,我们对最先进的数据集的实验与我们的理论见解完全一致,并确认了我们算法的卓越性能。最后,对于不平衡的高斯 - 混合数据,我们执行泛化分析,揭示平衡/标准错误和相同机会之间的权衡。
translated by 谷歌翻译
由于它们对社会决策产生至关重要的影响,因此AI算法不仅应该是准确的,而且应该是公平的。在公平性AI的各种算法中,通过最大程度地降低受特定公平限制的经验风险(例如,跨熵)来学习预测模型。但是,为避免计算困难,给定的公平限制被替代公平限制代替,因为0-1损失被分类问题的凸替代损失所取代。在本文中,我们调查了现有的替代公平限制的有效性,并提出了一种称为幻灯片的新替代公平约束,该公平性在计算上是可行的,并且在渐近上有效,从而使学识渊博的模型无效地满足公平性约束并实现快速融合率。数值实验证实,幻灯片适用于各种基准数据集。
translated by 谷歌翻译
我们研究随机梯度下降(SGD)在多大程度上被理解为“常规”学习规则,该规则通过获得良好的培训数据来实现概括性能。我们考虑基本的随机凸优化框架,其中(一通道,无需替代)SGD在经典上是众所周知的,可以最大程度地降低人口风险,以$ o(1/\ sqrt n)$ $ O(1/\ sqrt n)$,并且出人意料地证明,存在问题实例SGD解决方案既表现出$ \ omega(1)$的经验风险和概括差距。因此,事实证明,从任何意义上讲,SGD在算法上都不是稳定的,并且其概括能力不能通过均匀的收敛性或任何其他当前已知的概括性结合技术来解释(除了其经典分析外)。然后,我们继续分析与替代SGD密切相关的相关性,为此我们表明不会发生类似现象,并证明其人口风险实际上确实以最佳速度融合。最后,我们在没有替换SGD的背景下解释了我们的主要结果,用于有限的和凸优化问题,并得出多上类别制度的上限和下限,从而在先前已知的结果上有了显着改善。
translated by 谷歌翻译
联邦学习(FL)是一种越来越受欢迎的机器学习范式,其中多个节点在隐私,通信和多个异质性约束下尝试协同学习。联邦学习中的持续存在问题是,不清楚优化目标应该:监督学习的标准平均风险最小化在处理联合学习的几个主要限制方面是不充分的,例如沟通适应性和个性化控制。我们在联合学习的框架中识别几个关键的Desiderata,并介绍了一个新的框架,Flix,考虑到联合学习所带来的独特挑战。 Flix具有标准的有限和形式,使从业者能够利用分布式优化的现有(潜在非本地)方法的巨大财富。通过不需要任何通信的智能初始化,Flix不需要使用本地步骤,但仍然可以通过本地方法执行不一致的正则化。我们提供了几种用于在通信约束下有效解决FLIX制剂的算法。最后,我们通过广泛的实验证实了我们的理论结果。
translated by 谷歌翻译
成对学习是指损失函数取决于一对情况的学习任务。它实例化了许多重要的机器学习任务,如双级排名和度量学习。一种流行的方法来处理成对学习中的流数据是在线梯度下降(OGD)算法,其中需要将当前实例配对以前具有足够大的尺寸的先前实例的电流实例,因此遭受可扩展性问题。在本文中,我们提出了用于成对学习的简单随机和在线梯度下降方法。与现有研究的显着差异是,我们仅将当前实例与前一个构建梯度方向配对,这在存储和计算复杂性中是有效的。我们为凸和非凸起的展示结果,优化和泛化误差界以及平滑和非光滑问题都开发了新颖的稳定性结果,优化和泛化误差界限。我们引入了新颖的技术来解耦模型的依赖性和前一个例子在优化和泛化分析中。我们的研究解决了使用具有非常小的固定尺寸的缓冲集开发OGD的有意义的泛化范围的开放问题。我们还扩展了我们的算法和稳定性分析,以便为成对学习开发差异私有的SGD算法,这显着提高了现有结果。
translated by 谷歌翻译
We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is algorithmically stable in the sense of Bousquet and Elisseeff. Our analysis only employs elementary tools from convex and continuous optimization. We derive stability bounds for both convex and non-convex optimization under standard Lipschitz and smoothness assumptions.Applying our results to the convex case, we provide new insights for why multiple epochs of stochastic gradient methods generalize well in practice. In the non-convex case, we give a new interpretation of common practices in neural networks, and formally show that popular techniques for training large deep models are indeed stability-promoting. Our findings conceptually underscore the importance of reducing training time beyond its obvious benefit.
translated by 谷歌翻译