Machine learning models (e.g., speech recognizers) are usually trained to minimize average loss, which results in representation disparityminority groups (e.g., non-native speakers) contribute less to the training objective and thus tend to suffer higher loss. Worse, as model accuracy affects user retention, a minority group can shrink over time. In this paper, we first show that the status quo of empirical risk minimization (ERM) amplifies representation disparity over time, which can even make initially fair models unfair. To mitigate this, we develop an approach based on distributionally robust optimization (DRO), which minimizes the worst case risk over all distributions close to the empirical distribution. We prove that this approach controls the risk of the minority group at each time step, in the spirit of Rawlsian distributive justice, while remaining oblivious to the identity of the groups. We demonstrate that DRO prevents disparity amplification on examples where ERM fails, and show improvements in minority group user satisfaction in a real-world text autocomplete task.
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
尽管现代的大规模数据集通常由异质亚群(例如,多个人口统计组或多个文本语料库)组成 - 最小化平均损失的标准实践并不能保证所有亚人群中均匀的低损失。我们提出了一个凸面程序,该过程控制给定尺寸的所有亚群中最差的表现。我们的程序包括有限样本(非参数)收敛的保证,可以保证最坏的亚群。从经验上讲,我们观察到词汇相似性,葡萄酒质量和累犯预测任务,我们最糟糕的程序学习了对不看到看不见的亚人群的模型。
translated by 谷歌翻译
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
对分发外概括的流行假设是训练数据包括子数据集,每个数据集每种分布从不同的分布中汲取;然后,目标是“插入”这些分布和“推断”超越它们 - 这一目标广泛称为域泛化。常见的信念是,ERM可以插入但不推断,后者更困难,但这些索赔含糊不清,缺乏正式的理由。在这项工作中,我们通过在球员之间重新推广子组作为在线游戏,从而最大限度地减少风险和对手呈现新的测试分布。在基于副组可能性的重量和外推的现有概念下,我们严格证明外推比插值更难地更难,尽管它们的统计复杂性没有显着差异。此外,我们表明ERM - 或嘈杂的变体 - 对于两个任务来说都是最佳的最佳状态。我们的框架为域泛化算法的正式分析提供了一个新的途径,这可能具有独立兴趣。
translated by 谷歌翻译
许多现代化的机器学习任务需要具有高尾部性能的模型,即在数据集中最严格的样本上的高性能。该问题已广泛研究了算法公平,类别不平衡和风险敏感决策等领域。一种最大化模型的尾部性能的流行方法是最大限度地减少CVAR(风险条件值)损失,这计算了损失尾部的平均风险。然而,对于通过零一次损耗评估模型的分类任务,我们表明,如果分类器是确定性的,那么平均零一个损耗的最小值也会最小化CVAR零一次损耗,表明CVAR损耗最小化是最小化的没有额外的假设没有帮助。我们通过最大限度地减少随机分类器的CVAR损失来规避这种负面结果,其中平均零一个损耗和CVAR零一次损耗的最小化器不再相同,因此最小化后者可能导致更好的尾部性能。为了学习这样的随机分类器,我们提出了增强的CVAR分类框架,该框架通过CVAR与称为LPBoost的经典升压算法之间的直接关系而激励。基于此框架,我们设计了一种称为$ \ alpha $ -adalpboost的算法。我们在四个基准数据集中凭经验评估了我们所提出的算法,并显示它比确定性模型训练方法更高的尾部性能。
translated by 谷歌翻译
成功的深度学习模型往往涉及培训具有比训练样本数量更多的参数的神经网络架构。近年来已经广泛研究了这种超分子化的模型,并且通过双下降现象和通过优化景观的结构特性,从统计的角度和计算视角都建立了过分统计化的优点。尽管在过上分层的制度中深入学习架构的显着成功,但也众所周知,这些模型对其投入中的小对抗扰动感到高度脆弱。即使在普遍培训的情况下,它们在扰动输入(鲁棒泛化)上的性能也会比良性输入(标准概括)的最佳可达到的性能更糟糕。因此,必须了解如何从根本上影响稳健性的情况下如何影响鲁棒性。在本文中,我们将通过专注于随机特征回归模型(具有随机第一层权重的两层神经网络)来提供超分度化对鲁棒性的作用的精确表征。我们考虑一个制度,其中样本量,输入维度和参数的数量彼此成比例地生长,并且当模型发生前列地训练时,可以为鲁棒泛化误差导出渐近精确的公式。我们的发达理论揭示了过分统计化对鲁棒性的非竞争效果,表明对于普遍训练的随机特征模型,高度公正化可能会损害鲁棒泛化。
translated by 谷歌翻译
我们研究了基于分布强大的机会约束的对抗性分类模型。我们表明,在Wasserstein模糊性下,该模型旨在最大限度地减少距离分类距离的条件值 - 风险,并且我们探讨了前面提出的对抗性分类模型和最大限度的分类机的链接。我们还提供了用于线性分类的分布鲁棒模型的重构,并且表明它相当于最小化正则化斜坡损失目标。数值实验表明,尽管这种配方的非凸起,但是标准的下降方法似乎会聚到全球最小值器。灵感来自这种观察,我们表明,对于某一类分布,正则化斜坡损失最小化问题的唯一静止点是全球最小化器。
translated by 谷歌翻译
数据驱动决策的经验风险最小化方法假设我们可以从与我们想要在下面部署的条件相同的条件下绘制的数据中学习决策规则。但是,在许多设置中,我们可能会担心我们的培训样本是有偏见的,并且某些组(以可观察或无法观察到的属性为特征)可能相对于一般人群而言是不足或代表过多的;在这种情况下,对培训集的经验风险最小化可能无法产生在部署时表现良好的规则。我们基于分配强大的优化和灵敏度分析的概念,我们提出了一种学习决策规则的方法,该方法将在测试分布家族的家庭中最小化最糟糕的案例风险,其有条件的结果分布$ y $ y $ y $ y $ x $有所不同有条件的训练分布最多是一个恒定因素,并且相对于训练数据的协变量分布,其协变量分布绝对是连续的。我们应用Rockafellar和Uryasev的结果表明,此问题等同于增强的凸风险最小化问题。我们提供了使用筛子的方法来学习健壮模型的统计保证,并提出了一种深度学习算法,其损失函数捕获了我们的稳健性目标。我们从经验上验证了我们在模拟中提出的方法和使用MIMIC-III数据集的案例研究。
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
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
Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the ǫ-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving machine learning algorithm design. This method entails perturbing the objective function before optimizing over classifiers. If the loss and regularizer satisfy certain convexity and differentiability criteria, we prove theoretical results showing that our algorithms preserve privacy, and provide generalization bounds for linear and nonlinear kernels. We further present a privacy-preserving technique for tuning the parameters in general machine learning algorithms, thereby providing end-to-end privacy guarantees for the training process. We apply these results to produce privacy-preserving analogues of regularized logistic regression and support vector machines. We obtain encouraging results from evaluating their performance on real demographic and benchmark data sets. Our results show that both theoretically and empirically, objective perturbation is superior to the previous state-of-the-art, output perturbation, in managing the inherent tradeoff between privacy and learning performance.
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
我们在对数损失下引入条件密度估计的过程,我们调用SMP(样本Minmax预测器)。该估算器最大限度地减少了统计学习的新一般过度风险。在标准示例中,此绑定量表为$ d / n $,$ d $ d $模型维度和$ n $ sample大小,并在模型拼写条目下批判性仍然有效。作为一个不当(超出型号)的程序,SMP在模型内估算器(如最大似然估计)的内部估算器上,其风险过高的风险降低。相比,与顺序问题的方法相比,我们的界限删除了SubOltimal $ \ log n $因子,可以处理无限的类。对于高斯线性模型,SMP的预测和风险受到协变量的杠杆分数,几乎匹配了在没有条件的线性模型的噪声方差或近似误差的条件下匹配的最佳风险。对于Logistic回归,SMP提供了一种非贝叶斯方法来校准依赖于虚拟样本的概率预测,并且可以通过解决两个逻辑回归来计算。它达到了$ O的非渐近风险((d + b ^ 2r ^ 2)/ n)$,其中$ r $绑定了特征的规范和比较参数的$ B $。相比之下,在模型内估计器内没有比$ \ min达到更好的速率({b r} / {\ sqrt {n}},{d e ^ {br} / {n})$。这为贝叶斯方法提供了更实用的替代方法,这需要近似的后部采样,从而部分地解决了Foster等人提出的问题。 (2018)。
translated by 谷歌翻译
Overparameterized neural networks can be highly accurate on average on an i.i.d.test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such groups). Distributionally robust optimization (DRO) allows us to learn models that instead minimize the worst-case training loss over a set of pre-defined groups. However, we find that naively applying group DRO to overparameterized neural networks fails: these models can perfectly fit the training data, and any model with vanishing average training loss also already has vanishing worst-case training loss. Instead, the poor worst-case performance arises from poor generalization on some groups. By coupling group DRO models with increased regularization-a stronger-than-typical 2 penalty or early stopping-we achieve substantially higher worst-group accuracies, with 10-40 percentage point improvements on a natural language inference task and two image tasks, while maintaining high average accuracies. Our results suggest that regularization is important for worst-group generalization in the overparameterized regime, even if it is not needed for average generalization. Finally, we introduce a stochastic optimization algorithm, with convergence guarantees, to efficiently train group DRO models.
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
Learned classifiers should often possess certain invariance properties meant to encourage fairness, robustness, or out-of-distribution generalization. However, multiple recent works empirically demonstrate that common invariance-inducing regularizers are ineffective in the over-parameterized regime, in which classifiers perfectly fit (i.e. interpolate) the training data. This suggests that the phenomenon of ``benign overfitting," in which models generalize well despite interpolating, might not favorably extend to settings in which robustness or fairness are desirable. In this work we provide a theoretical justification for these observations. We prove that -- even in the simplest of settings -- any interpolating learning rule (with arbitrarily small margin) will not satisfy these invariance properties. We then propose and analyze an algorithm that -- in the same setting -- successfully learns a non-interpolating classifier that is provably invariant. We validate our theoretical observations on simulated data and the Waterbirds dataset.
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
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
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