The spectra of random feature matrices provide essential information on the conditioning of the linear system used in random feature regression problems and are thus connected to the consistency and generalization of random feature models. Random feature matrices are asymmetric rectangular nonlinear matrices depending on two input variables, the data and the weights, which can make their characterization challenging. We consider two settings for the two input variables, either both are random variables or one is a random variable and the other is well-separated, i.e. there is a minimum distance between points. With conditions on the dimension, the complexity ratio, and the sampling variance, we show that the singular values of these matrices concentrate near their full expectation and near one with high-probability. In particular, since the dimension depends only on the logarithm of the number of random weights or the number of data points, our complexity bounds can be achieved even in moderate dimensions for many practical setting. The theoretical results are verified with numerical experiments.
translated by 谷歌翻译
我们在随机特征矩阵的条件数上提供(高概率)界限。特别是,我们表明,如果复杂性比率$ \ frac {n} $ where $ n $是n $ with n $ wore $ n $是$ m $的数量,如$ \ log ^ {-1}( n)$或$ \ log(m)$,然后随机功能矩阵很好。该结果在没有正则化的情况下保持并且依赖于在随机特征矩阵的相关组件之间建立各种浓度界限。另外,我们在随机特征矩阵的受限等距常数上获得界限。我们证明了使用随机特征矩阵的回归问题相关的风险表现出双重下降现象,并且这是条件数的双缩小行为的效果。风险范围包括使用最小二乘问题的underParamedAimed设置和使用最小规范插值问题或稀疏回归问题的过次参数化设置。对于最小二乘或稀疏的回归案例,我们表明风险降低为$ M $和$ N $增加,即使在存在有限或随机噪声时也是如此。风险绑定与文献中的最佳缩放匹配,我们的结果中的常量是显式的,并且独立于数据的维度。
translated by 谷歌翻译
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.
translated by 谷歌翻译
We consider the random feature ridge regression (RFRR) given by a two-layer neural network at random initialization. We study the non-asymptotic behaviors of the training error, cross-validations, and generalization error of RFRR with nearly orthogonal deterministic input data in the overparameterized regime, where the number of parameters $N$ is much larger than the sample size $n$. We respectively establish the concentrations of the training errors, cross-validations, and generalization errors of RFRR around their corresponding errors of kernel ridge regression (KRR). This KRR is defined by an expected kernel from a random feature map. We then approximate the performances of the KRR by a polynomial kernel matrix, whose degree only depends on the orthogonality among different input vectors. The degree of this polynomial kernel essentially determines the asymptotic behavior of RFRR and KRR. Our results hold for a general class of target functions and input data with weak approximate orthonormal properties among different data points. Based on these approximations and nearly orthogonality, we obtain a lower bound for the generalization error of RFRR.
translated by 谷歌翻译
过度分化的神经网络倾向于完全符合嘈杂的训练数据,但在测试数据上概括。灵感来自这一实证观察,最近的工作试图了解在更简单的线性模型中的良性过度或无害插值的这种现象。以前的理论工作批判性地假设数据特征是统计独立的,或者输入数据是高维的;这会阻止具有结构化特征映射的一般非参数设置。在本文中,我们为再生内核希尔伯特空间中的上限回归和分类风险提供了一般和灵活的框架。关键贡献是我们的框架在数据革处矩阵上描述了精确的充分条件,在这种情况下发生无害的插值。我们的结果恢复了现有的独立功能结果(具有更简单的分析),但它们还表明,在更常规的环境中可能发生无害的插值,例如有界正常系统的功能。此外,我们的结果表明,以先前仅针对高斯特征的方式显示分类和回归性能之间的渐近分离。
translated by 谷歌翻译
现代神经网络通常以强烈的过度构造状态运行:它们包含许多参数,即使实际标签被纯粹随机的标签代替,它们也可以插入训练集。尽管如此,他们在看不见的数据上达到了良好的预测错误:插值训练集并不会导致巨大的概括错误。此外,过度散色化似乎是有益的,因为它简化了优化景观。在这里,我们在神经切线(NT)制度中的两层神经网络的背景下研究这些现象。我们考虑了一个简单的数据模型,以及各向同性协变量的矢量,$ d $尺寸和$ n $隐藏的神经元。我们假设样本量$ n $和尺寸$ d $都很大,并且它们在多项式上相关。我们的第一个主要结果是对过份术的经验NT内核的特征结构的特征。这种表征意味着必然的表明,经验NT内核的最低特征值在$ ND \ gg n $后立即从零界限,因此网络可以在同一制度中精确插值任意标签。我们的第二个主要结果是对NT Ridge回归的概括误差的表征,包括特殊情况,最小值-ULL_2 $ NORD插值。我们证明,一旦$ nd \ gg n $,测试误差就会被内核岭回归之一相对于无限宽度内核而近似。多项式脊回归的误差依次近似后者,从而通过与激活函数的高度组件相关的“自我诱导的”项增加了正则化参数。多项式程度取决于样本量和尺寸(尤其是$ \ log n/\ log d $)。
translated by 谷歌翻译
对于由缺陷线性回归中的标签噪声引起的预期平均平方概率,我们证明了无渐近分布的下限。我们的下部结合概括了过度公共数据(内插)制度的类似已知结果。与最先前的作品相比,我们的分析适用于广泛的输入分布,几乎肯定的全排列功能矩阵,允许我们涵盖各种类型的确定性或随机特征映射。我们的下限是渐近的锐利,暗示在存在标签噪声时,缺陷的线性回归不会在任何这些特征映射中围绕内插阈值进行良好的。我们详细分析了强加的假设,并为分析(随机)特征映射提供了理论。使用此理论,我们可以表明我们的假设对于具有(Lebesgue)密度的输入分布以及随机深神经网络给出的特征映射,具有Sigmoid,Tanh,SoftPlus或Gelu等分析激活功能。作为进一步的例子,我们示出了来自随机傅里叶特征和多项式内核的特征映射也满足我们的假设。通过进一步的实验和分析结果,我们补充了我们的理论。
translated by 谷歌翻译
本文探讨了可变参数化模型系列的线性回归的概括性损失,包括在参数化和过度参数化的模型中。我们表明,泛化曲线可以具有任意数量的峰值,而且可以明确地控制这些峰的位置。我们的结果突出了经典U形泛化曲线和最近观察到的双下降曲线的事实不是模型系列的内在特性。相反,它们的出现是由于数据的性质与学习算法的感应偏差之间的相互作用。
translated by 谷歌翻译
我们研究了非参数脊的最小二乘的学习属性。特别是,我们考虑常见的估计人的估计案例,由比例依赖性内核定义,并专注于规模的作用。这些估计器内插数据,可以显示规模来通过条件号控制其稳定性。我们的分析表明,这是不同的制度,具体取决于样本大小,其尺寸与问题的平滑度之间的相互作用。实际上,当样本大小小于数据维度中的指数时,可以选择比例,以便学习错误减少。随着样本尺寸变大,总体错误停止减小但有趣地可以选择规模,使得噪声引起的差异仍然存在界线。我们的分析结合了概率,具有来自插值理论的许多分析技术。
translated by 谷歌翻译
随机奇异值分解(RSVD)是用于计算大型数据矩阵截断的SVD的一类计算算法。给定A $ n \ times n $对称矩阵$ \ mathbf {m} $,原型RSVD算法输出通过计算$ \ mathbf {m mathbf {m} $的$ k $引导singular vectors的近似m}^{g} \ mathbf {g} $;这里$ g \ geq 1 $是一个整数,$ \ mathbf {g} \ in \ mathbb {r}^{n \ times k} $是一个随机的高斯素描矩阵。在本文中,我们研究了一般的“信号加上噪声”框架下的RSVD的统计特性,即,观察到的矩阵$ \ hat {\ mathbf {m}} $被认为是某种真实但未知的加法扰动信号矩阵$ \ mathbf {m} $。我们首先得出$ \ ell_2 $(频谱规范)和$ \ ell_ {2 \ to \ infty} $(最大行行列$ \ ell_2 $ norm)$ \ hat {\ hat {\ Mathbf {M}} $和信号矩阵$ \ Mathbf {M} $的真实单数向量。这些上限取决于信噪比(SNR)和功率迭代$ g $的数量。观察到一个相变现象,其中较小的SNR需要较大的$ g $值以保证$ \ ell_2 $和$ \ ell_ {2 \ to \ fo \ infty} $ distances的收敛。我们还表明,每当噪声矩阵满足一定的痕量生长条件时,这些相变发生的$ g $的阈值都会很清晰。最后,我们得出了近似奇异向量的行波和近似矩阵的进入波动的正常近似。我们通过将RSVD的几乎最佳性能保证在应用于三个统计推断问题的情况下,即社区检测,矩阵完成和主要的组件分析,并使用缺失的数据来说明我们的理论结果。
translated by 谷歌翻译
混合模型的学习可以看作是聚类问题。实际上,给定根据分布混合物独立生成的数据样本,我们经常希望根据样品的{\ IT正确靶向群集},根据它们从哪个组件分布中生成的样品。对于聚类问题,从业人员通常选择使用简单的$ k $ -MEANS算法。 $ k $ -Means试图找到一个{\ it最佳聚类},该{\ it clustering}将每个点与其群集中心之间的平方距离最小化。在本文中,我们考虑通过优化方形距离获得的解决方案(群集)的基本(即信息理论)极限。特别是,假设数据样本是从球形高斯分布的混合物中生成的,我们为任何最佳聚类和正确的目标聚类提供了足够的条件。我们还将结果概括为对数符号分布。此外,我们表明,在混合模型上相似甚至较弱的条件下,具有降低尺寸的样品的任何最佳聚类也接近正确的目标群集。这些结果为$ k $ -Means(有或没有降低尺寸降低)的信息提供了直觉,作为学习混合模型的算法。
translated by 谷歌翻译
支持向量机(SVM)是一种完善的分类方法,其名称指的是称为支持向量的特定训练示例,该示例确定了分离超平面的最大边缘。与培训示例相比,当支持向量的数量少时,SVM分类器享有良好的概括属性。但是,最近的研究表明,在足够高维的线性分类问题中,尽管支持向量的扩散,但在所有训练示例都是支持向量的情况下,SVM仍可以很好地概括。在本文中,我们确定了这种支持矢量增殖现象的新的确定性等效性,并使用它们来(1)实质上扩大了该现象在高维环境中发生的条件,并且(2)证明了几乎匹配的逆向结果。
translated by 谷歌翻译
我们系统地{研究基于内核的图形laplacian(gl)的光谱},该图在非null设置中由高维和嘈杂的随机点云构成,其中点云是从低维几何对象(如歧管)中采样的,被高维噪音破坏。我们量化了信号和噪声在信号噪声比(SNR)的不同状态下如何相互作用,并报告GL的{所产生的特殊光谱行为}。此外,我们还探索了GL频谱上的内核带宽选择,而SNR的不同状态则导致带宽的自适应选择,这与实际数据中的共同实践相吻合。该结果为数据集嘈杂时的从业人员提供了理论支持。
translated by 谷歌翻译
神经切线内核(NTK)已成为提供记忆,优化和泛化的强大工具,可保证深度神经网络。一项工作已经研究了NTK频谱的两层和深网,其中至少具有$ \ omega(n)$神经元的层,$ n $是培训样本的数量。此外,有越来越多的证据表明,只要参数数量超过样品数量,具有亚线性层宽度的深网是强大的记忆和优化器。因此,一个自然的开放问题是NTK是否在如此充满挑战的子线性设置中适应得很好。在本文中,我们以肯定的方式回答了这个问题。我们的主要技术贡献是对最小的深网的最小NTK特征值的下限,最小可能的过度参数化:参数的数量大约为$ \ omega(n)$,因此,神经元的数量仅为$ $ $ \ omega(\ sqrt {n})$。为了展示我们的NTK界限的适用性,我们为梯度下降训练提供了两个有关记忆能力和优化保证的结果。
translated by 谷歌翻译
通过梯度流优化平均平衡误差,研究了功能空间中神经网络的动态。我们认为,在underParameterized制度中,网络了解由与其特征值对应的率的神经切线内核(NTK)确定的整体运算符$ t_ {k ^ \ infty} $的特征功能。例如,对于SPENTE $ S ^ {D-1} $和旋转不变的权重分配的均匀分布式数据,$ t_ {k ^ \ infty} $的特征函数是球形谐波。我们的结果可以理解为描述interparameterized制度中的光谱偏压。证据使用“阻尼偏差”的概念,其中NTK物质对具有由于阻尼因子的发生而具有大特征值的特征的偏差。除了下公共条例的制度之外,阻尼偏差可用于跟踪过度分辨率设置中经验风险的动态,允许我们在文献中延长某些结果。我们得出结论,阻尼偏差在优化平方误差时提供了动态的简单和统一的视角。
translated by 谷歌翻译
Classical asymptotic theory for statistical inference usually involves calibrating a statistic by fixing the dimension $d$ while letting the sample size $n$ increase to infinity. Recently, much effort has been dedicated towards understanding how these methods behave in high-dimensional settings, where $d$ and $n$ both increase to infinity together. This often leads to different inference procedures, depending on the assumptions about the dimensionality, leaving the practitioner in a bind: given a dataset with 100 samples in 20 dimensions, should they calibrate by assuming $n \gg d$, or $d/n \approx 0.2$? This paper considers the goal of dimension-agnostic inference; developing methods whose validity does not depend on any assumption on $d$ versus $n$. We introduce an approach that uses variational representations of existing test statistics along with sample splitting and self-normalization to produce a new test statistic with a Gaussian limiting distribution, regardless of how $d$ scales with $n$. The resulting statistic can be viewed as a careful modification of degenerate U-statistics, dropping diagonal blocks and retaining off-diagonal blocks. We exemplify our technique for some classical problems including one-sample mean and covariance testing, and show that our tests have minimax rate-optimal power against appropriate local alternatives. In most settings, our cross U-statistic matches the high-dimensional power of the corresponding (degenerate) U-statistic up to a $\sqrt{2}$ factor.
translated by 谷歌翻译
最近的一项工作已经通过神经切线核(NTK)分析了深神经网络的理论特性。特别是,NTK的最小特征值与记忆能力,梯度下降算法的全球收敛性和深网的概括有关。但是,现有结果要么在两层设置中提供边界,要么假设对于多层网络,将NTK矩阵的频谱从0界限为界限。在本文中,我们在无限宽度和有限宽度的限制情况下,在最小的ntk矩阵的最小特征值上提供了紧密的界限。在有限宽度的设置中,我们认为的网络体系结构相当笼统:我们需要大致订购$ n $神经元的宽层,$ n $是数据示例的数量;剩余层宽度的缩放是任意的(取决于对数因素)。为了获得我们的结果,我们分析了各种量的独立兴趣:我们对隐藏特征矩阵的最小奇异值以及输入输出特征图的Lipschitz常数上的上限给出了下限。
translated by 谷歌翻译
The kernel Maximum Mean Discrepancy~(MMD) is a popular multivariate distance metric between distributions that has found utility in two-sample testing. The usual kernel-MMD test statistic is a degenerate U-statistic under the null, and thus it has an intractable limiting distribution. Hence, to design a level-$\alpha$ test, one usually selects the rejection threshold as the $(1-\alpha)$-quantile of the permutation distribution. The resulting nonparametric test has finite-sample validity but suffers from large computational cost, since every permutation takes quadratic time. We propose the cross-MMD, a new quadratic-time MMD test statistic based on sample-splitting and studentization. We prove that under mild assumptions, the cross-MMD has a limiting standard Gaussian distribution under the null. Importantly, we also show that the resulting test is consistent against any fixed alternative, and when using the Gaussian kernel, it has minimax rate-optimal power against local alternatives. For large sample sizes, our new cross-MMD provides a significant speedup over the MMD, for only a slight loss in power.
translated by 谷歌翻译
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.
translated by 谷歌翻译
通常希望通过将其投影到低维子空间来降低大数据集的维度。矩阵草图已成为一种非常有效地执行这种维度降低的强大技术。尽管有关于草图最差的表现的广泛文献,但现有的保证通常与实践中观察到的差异截然不同。我们利用随机矩阵的光谱分析中的最新发展来开发新技术,这些技术为通过素描获得的随机投影矩阵的期望值提供了准确的表达。这些表达式可以用来表征各种常见的机器学习任务中尺寸降低的性能,从低级别近似到迭代随机优化。我们的结果适用于几种流行的草图方法,包括高斯和拉德马赫草图,它们可以根据数据的光谱特性对这些方法进行精确的分析。经验结果表明,我们得出的表达式反映了这些草图方法的实际性能,直到低阶效应甚至不变因素。
translated by 谷歌翻译