我们考虑在有限数据设置下一般损失函数下线性分类问题。过度装备是这里的常见问题。防止过度装备的标准方法是减少和正则化的维度。但是减少了维度的丢失信息，而正规化要求用户选择规范，或之前或距离度量。我们提出了一种称为Rolin的算法，不需要用户选择并适用于大类丢失功能。 Rolin将顶部主成分的可靠信息与强大的优化组合，以从不可靠的子空间中提取任何有用的信息。它还包括一种新的强大交叉验证，比有限数据设置中的现有交叉验证方法更好。在$ 25 $现实世界数据集和三个标准损失功能的实验表明，Rolin广泛优于维度，减少和正规。与Rolin相比，维数减少有14 \％ - 40 \％$较差的测试损失。防止$ L_1 $和$ L_2 $正则化，Rolin可以更好地为3倍，对于平方铰链损耗更好的逻辑损耗和12倍。对于小型样本尺寸，差异最大，其中Rolin实现了比任何竞争方法更多的数据集的2倍至3x的最佳损失。对于某些数据集，Rolin以$ 15 $培训样本比为1500美元的最佳规范正常化更好。

许多最近的作品表明，过度分辨率隐含地降低了MIN-NORM Interpolator和Max-Maxifiers的方差。这些调查结果表明，RIDGE正则化在高维度下具有消失的益处。我们通过表明，即使在没有噪声的情况下，避免通过脊正则化的插值可以显着提高泛化。我们证明了这种现象，用于线性回归和分类的强大风险，因此提供了强大的过度装备的第一个理论结果。

有监督的分类技术使用培训样本来学习具有小预期0-1损失（错误概率）的分类规则。常规方法可以通过使用替代损失而不是0-1损失并考虑特定的规则家族（假设类别）来实现可拖动学习并提供样本外的概括。本文介绍了Minimax风险分类器（MRCS），该分类器将最差的0-1损失比一般分类规则最小化，并在学习时提供严格的绩效保证。我们表明，使用特征内核给出的特征映射非常普遍地一致。本文还提出了MRC学习的有效优化技术，并表明提出的方法可以提供准确的分类以及实践中的紧张性能保证。

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。

We study a multi-factor block model for variable clustering and connect it to the regularized subspace clustering by formulating a distributionally robust version of the nodewise regression. To solve the latter problem, we derive a convex relaxation, provide guidance on selecting the size of the robust region, and hence the regularization weighting parameter, based on the data, and propose an ADMM algorithm for implementation. We validate our method in an extensive simulation study. Finally, we propose and apply a variant of our method to stock return data, obtain interpretable clusters that facilitate portfolio selection and compare its out-of-sample performance with other clustering methods in an empirical study.

监督主体组件分析（SPCA）的方法旨在将标签信息纳入主成分分析（PCA），以便提取的功能对于预测感兴趣的任务更有用。SPCA的先前工作主要集中在优化预测误差上，并忽略了提取功能解释的最大化方差的价值。我们为SPCA提出了一种新的方法，该方法共同解决了这两个目标，并从经验上证明我们的方法主导了现有方法，即在预测误差和变异方面都超越了它们的表现。我们的方法可容纳任意监督的学习损失，并通过统计重新制定提供了广义线性模型的新型低级扩展。

In many modern applications of deep learning the neural network has many more parameters than the data points used for its training. Motivated by those practices, a large body of recent theoretical research has been devoted to studying overparameterized models. One of the central phenomena in this regime is the ability of the model to interpolate noisy data, but still have test error lower than the amount of noise in that data. arXiv:1906.11300 characterized for which covariance structure of the data such a phenomenon can happen in linear regression if one considers the interpolating solution with minimum $\ell_2$-norm and the data has independent components: they gave a sharp bound on the variance term and showed that it can be small if and only if the data covariance has high effective rank in a subspace of small co-dimension. We strengthen and complete their results by eliminating the independence assumption and providing sharp bounds for the bias term. Thus, our results apply in a much more general setting than those of arXiv:1906.11300, e.g., kernel regression, and not only characterize how the noise is damped but also which part of the true signal is learned. Moreover, we extend the result to the setting of ridge regression, which allows us to explain another interesting phenomenon: we give general sufficient conditions under which the optimal regularization is negative.

我们开发了快速算法和可靠软件，以凸出具有Relu激活功能的两层神经网络的凸优化。我们的工作利用了标准的重量罚款训练问题作为一组组-YELL_1 $调查的数据本地模型的凸重新印度，其中局部由多面体锥体约束强制执行。在零规范化的特殊情况下，我们表明此问题完全等同于凸“ Gated Relu”网络的不受约束的优化。对于非零正则化的问题，我们表明凸面式relu模型获得了RELU训练问题的数据依赖性近似范围。为了优化凸的重新制定，我们开发了一种加速的近端梯度方法和实用的增强拉格朗日求解器。我们表明，这些方法比针对非凸问题（例如SGD）和超越商业内部点求解器的标准训练启发式方法要快。在实验上，我们验证了我们的理论结果，探索组-ELL_1 $正则化路径，并对神经网络进行比例凸的优化，以在MNIST和CIFAR-10上进行图像分类。

从外界培训的机器学习模型可能会被数据中毒攻击损坏，将恶意指向到模型的培训集中。对这些攻击的常见防御是数据消毒：在培训模型之前首先过滤出异常培训点。在本文中，我们开发了三次攻击，可以绕过广泛的常见数据消毒防御，包括基于最近邻居，训练损失和奇异值分解的异常探测器。通过增加3％的中毒数据，我们的攻击成功地将Enron垃圾邮件检测数据集的测试错误从3％增加到24％，并且IMDB情绪分类数据集从12％到29％。相比之下，没有明确占据这些数据消毒防御的现有攻击被他们击败。我们的攻击基于两个想法：（i）我们协调我们的攻击将中毒点彼此放置在彼此附近，（ii）我们将每个攻击制定为受限制的优化问题，限制旨在确保中毒点逃避检测。随着这种优化涉及解决昂贵的Bilevel问题，我们的三个攻击对应于基于影响功能的近似近似这个问题的方式; minimax二元性;和karush-kuhn-tucker（kkt）条件。我们的结果强调了对数据中毒攻击产生更强大的防御的必要性。

Low-rank matrix approximations, such as the truncated singular value decomposition and the rank-revealing QR decomposition, play a central role in data analysis and scientific computing. This work surveys and extends recent research which demonstrates that randomization offers a powerful tool for performing low-rank matrix approximation. These techniques exploit modern computational architectures more fully than classical methods and open the possibility of dealing with truly massive data sets.This paper presents a modular framework for constructing randomized algorithms that compute partial matrix decompositions. These methods use random sampling to identify a subspace that captures most of the action of a matrix. The input matrix is then compressed-either explicitly or implicitly-to this subspace, and the reduced matrix is manipulated deterministically to obtain the desired low-rank factorization. In many cases, this approach beats its classical competitors in terms of accuracy, speed, and robustness. These claims are supported by extensive numerical experiments and a detailed error analysis.The specific benefits of randomized techniques depend on the computational environment. Consider the model problem of finding the k dominant components of the singular value decomposition of an m × n matrix. (i) For a dense input matrix, randomized algorithms require O(mn log(k)) floating-point operations (flops) in contrast with O(mnk) for classical algorithms. (ii) For a sparse input matrix, the flop count matches classical Krylov subspace methods, but the randomized approach is more robust and can easily be reorganized to exploit multi-processor architectures. (iii) For a matrix that is too large to fit in fast memory, the randomized techniques require only a constant number of passes over the data, as opposed to O(k) passes for classical algorithms. In fact, it is sometimes possible to perform matrix approximation with a single pass over the data.

Learning curves provide insight into the dependence of a learner's generalization performance on the training set size. This important tool can be used for model selection, to predict the effect of more training data, and to reduce the computational complexity of model training and hyperparameter tuning. This review recounts the origins of the term, provides a formal definition of the learning curve, and briefly covers basics such as its estimation. Our main contribution is a comprehensive overview of the literature regarding the shape of learning curves. We discuss empirical and theoretical evidence that supports well-behaved curves that often have the shape of a power law or an exponential. We consider the learning curves of Gaussian processes, the complex shapes they can display, and the factors influencing them. We draw specific attention to examples of learning curves that are ill-behaved, showing worse learning performance with more training data. To wrap up, we point out various open problems that warrant deeper empirical and theoretical investigation. All in all, our review underscores that learning curves are surprisingly diverse and no universal model can be identified.

最近有兴趣的兴趣在教师学生环境中的各种普遍性线性估计问题中的渐近重建性能研究，特别是对于I.I.D标准正常矩阵的案例。在这里，我们超越这些矩阵，并证明了具有具有任意界限频谱的旋转不变数据矩阵的凸遍的线性模型的重建性能的分析公式，严格地确认使用来自统计物理的副本衍生的猜想。该公式包括许多问题，例如压缩感测或稀疏物流分类。通过利用消息通过算法和迭代的统计特性来实现证明，允许表征估计器的渐近实证分布。我们的证据是基于构建Oracle多层向量近似消息传递算法的会聚序列的构建，其中通过检查等效动态系统的稳定性来完成收敛分析。我们说明了我们对主流学习方法的数值示例的要求，例如稀疏的逻辑回归和线性支持矢量分类器，显示中等大小模拟和渐近预测之间的良好一致性。

We study distributionally robust optimization (DRO) with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We provide convex programming dual reformulation for a general nominal distribution. Compared with Wasserstein DRO, it is computationally tractable for a larger class of loss functions, and its worst-case distribution is more reasonable. We propose an efficient first-order algorithm with bisection search to solve the dual reformulation. We demonstrate that our proposed algorithm finds $\delta$-optimal solution of the new DRO formulation with computation cost $\tilde{O}(\delta^{-3})$ and memory cost $\tilde{O}(\delta^{-2})$, and the computation cost further improves to $\tilde{O}(\delta^{-2})$ when the loss function is smooth. Finally, we provide various numerical examples using both synthetic and real data to demonstrate its competitive performance and light computational speed.

异常值广泛发生在大数据应用中，可能严重影响统计估计和推理。在本文中，引入了抗强估计的框架，以强制任意给出的损耗函数。它与修剪方法密切连接，并且包括所有样本的显式外围参数，这反过来促进计算，理论和参数调整。为了解决非凸起和非体性的问题，我们开发可扩展的算法，以实现轻松和保证快速收敛。特别地，提出了一种新的技术来缓解对起始点的要求，使得在常规数据集上，可以大大减少数据重采样的数量。基于组合的统计和计算处理，我们能够超越M估计来执行非因思分析。所获得的抗性估算器虽然不一定全局甚至是局部最佳的，但在低维度和高维度中享有最小的速率最优性。回归，分类和神经网络的实验表明，在总异常值发生的情况下提出了拟议方法的优异性能。

The accuracy of k-nearest neighbor (kNN) classification depends significantly on the metric used to compute distances between different examples. In this paper, we show how to learn a Mahalanobis distance metric for kNN classification from labeled examples. The Mahalanobis metric can equivalently be viewed as a global linear transformation of the input space that precedes kNN classification using Euclidean distances. In our approach, the metric is trained with the goal that the k-nearest neighbors always belong to the same class while examples from different classes are separated by a large margin. As in support vector machines (SVMs), the margin criterion leads to a convex optimization based on the hinge loss. Unlike learning in SVMs, however, our approach requires no modification or extension for problems in multiway (as opposed to binary) classification. In our framework, the Mahalanobis distance metric is obtained as the solution to a semidefinite program. On several data sets of varying size and difficulty, we find that metrics trained in this way lead to significant improvements in kNN classification. Sometimes these results can be further improved by clustering the training examples and learning an individual metric within each cluster. We show how to learn and combine these local metrics in a globally integrated manner.

强大的机器学习模型的开发中的一个重要障碍是协变量的转变，当训练和测试集的输入分布时发生的分配换档形式在条件标签分布保持不变时发生。尽管现实世界应用的协变量转变普遍存在，但在现代机器学习背景下的理论理解仍然缺乏。在这项工作中，我们检查协变量的随机特征回归的精确高尺度渐近性，并在该设置中提出了限制测试误差，偏差和方差的精确表征。我们的结果激发了一种自然部分秩序，通过协变速转移，提供足够的条件来确定何时何时损害（甚至有助于）测试性能。我们发现，过度分辨率模型表现出增强的协会转变的鲁棒性，为这种有趣现象提供了第一个理论解释之一。此外，我们的分析揭示了分销和分发外概率性能之间的精确线性关系，为这一令人惊讶的近期实证观察提供了解释。

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。

监督字典学习（SDL）是一种经典的机器学习方法，同时寻求特征提取和分类任务，不一定是先验的目标。 SDL的目的是学习类歧视性词典，这是一组潜在特征向量，可以很好地解释特征以及观察到的数据的标签。在本文中，我们提供了SDL的系统研究，包括SDL的理论，算法和应用。首先，我们提供了一个新颖的框架，该框架将“提升” SDL作为组合因子空间中的凸问题，并提出了一种低级别的投影梯度下降算法，该算法将指数成倍收敛于目标的全局最小化器。我们还制定了SDL的生成模型，并根据高参数制度提供真实参数的全局估计保证。其次，我们被视为一个非convex约束优化问题，我们为SDL提供了有效的块坐标下降算法，该算法可以保证在$ O（\ varepsilon^{ - 1}（\ log）中找到$ \ varepsilon $ - 定位点（\ varepsilon \ varepsilon^{ - 1}）^{2}）$ iterations。对于相应的生成模型，我们为受约束和正则化的最大似然估计问题建立了一种新型的非反应局部一致性结果，这可能是独立的。第三，我们将SDL应用于监督主题建模和胸部X射线图像中的肺炎检测中，以进行不平衡的文档分类。我们还提供了模拟研究，以证明当最佳的重建性和最佳判别词典之间存在差异时，SDL变得更加有效。

本文评价用机器学习问题的数值优化方法。由于机器学习模型是高度参数化的，我们专注于适合高维优化的方法。我们在二次模型上构建直觉，以确定哪种方法适用于非凸优化，并在凸函数上开发用于这种方法的凸起函数。随着随机梯度下降和动量方法的这种理论基础，我们试图解释为什么机器学习领域通常使用的方法非常成功。除了解释成功的启发式之外，最后一章还提供了对更多理论方法的广泛审查，这在实践中并不像惯例。所以在某些情况下，这项工作试图回答这个问题：为什么默认值中包含的默认TensorFlow优化器？

Markowitz mean-variance portfolios with sample mean and covariance as input parameters feature numerous issues in practice. They perform poorly out of sample due to estimation error, they experience extreme weights together with high sensitivity to change in input parameters. The heavy-tail characteristics of financial time series are in fact the cause for these erratic fluctuations of weights that consequently create substantial transaction costs. In robustifying the weights we present a toolbox for stabilizing costs and weights for global minimum Markowitz portfolios. Utilizing a projected gradient descent (PGD) technique, we avoid the estimation and inversion of the covariance operator as a whole and concentrate on robust estimation of the gradient descent increment. Using modern tools of robust statistics we construct a computationally efficient estimator with almost Gaussian properties based on median-of-means uniformly over weights. This robustified Markowitz approach is confirmed by empirical studies on equity markets. We demonstrate that robustified portfolios reach the lowest turnover compared to shrinkage-based and constrained portfolios while preserving or slightly improving out-of-sample performance.