The study of stability and sensitivity of statistical methods or algorithms with respect to their data is an important problem in machine learning and statistics. The performance of the algorithm under resampling of the data is a fundamental way to measure its stability and is closely related to generalization or privacy of the algorithm. In this paper, we study the resampling sensitivity for the principal component analysis (PCA). Given an $ n \times p $ random matrix $ \mathbf{X} $, let $ \mathbf{X}^{[k]} $ be the matrix obtained from $ \mathbf{X} $ by resampling $ k $ randomly chosen entries of $ \mathbf{X} $. Let $ \mathbf{v} $ and $ \mathbf{v}^{[k]} $ denote the principal components of $ \mathbf{X} $ and $ \mathbf{X}^{[k]} $. In the proportional growth regime $ p/n \to \xi \in (0,1] $, we establish the sharp threshold for the sensitivity/stability transition of PCA. When $ k \gg n^{5/3} $, the principal components $ \mathbf{v} $ and $ \mathbf{v}^{[k]} $ are asymptotically orthogonal. On the other hand, when $ k \ll n^{5/3} $, the principal components $ \mathbf{v} $ and $ \mathbf{v}^{[k]} $ are asymptotically colinear. In words, we show that PCA is sensitive to the input data in the sense that resampling even a negligible portion of the input may completely change the output.
translated by 谷歌翻译
假设$ g $是根据所谓的HyperGraph随机块模型(HSBM)产生的,我们考虑了稀疏$ Q $均匀的HyperGraph $ G $中的社区检测问题。我们证明,基于非折线操作员的光谱方法具有很高的概率,可以降低到Angelini等人猜想的广义kesten-Stigum检测阈值。我们表征了稀疏HSBM的非背带操作员的频谱,并使用Ihara-Bass公式为超图提供有效的尺寸降低程序。结果,可以将稀疏HSBM的社区检测减少为$ 2N \ times 2n $非正态矩阵的特征向量问题,该矩阵从邻接矩阵和超级格雷普的学位矩阵中构建。据我们所知,这是第一种可证明,有效的光谱算法,它可以根据一般对称概率张量生成$ K $块的HSBMS阈值。
translated by 谷歌翻译
我们系统地{研究基于内核的图形laplacian(gl)的光谱},该图在非null设置中由高维和嘈杂的随机点云构成,其中点云是从低维几何对象(如歧管)中采样的,被高维噪音破坏。我们量化了信号和噪声在信号噪声比(SNR)的不同状态下如何相互作用,并报告GL的{所产生的特殊光谱行为}。此外,我们还探索了GL频谱上的内核带宽选择,而SNR的不同状态则导致带宽的自适应选择,这与实际数据中的共同实践相吻合。该结果为数据集嘈杂时的从业人员提供了理论支持。
translated by 谷歌翻译
现代神经网络通常以强烈的过度构造状态运行:它们包含许多参数,即使实际标签被纯粹随机的标签代替,它们也可以插入训练集。尽管如此,他们在看不见的数据上达到了良好的预测错误:插值训练集并不会导致巨大的概括错误。此外,过度散色化似乎是有益的,因为它简化了优化景观。在这里,我们在神经切线(NT)制度中的两层神经网络的背景下研究这些现象。我们考虑了一个简单的数据模型,以及各向同性协变量的矢量,$ 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
Motivated by the problem of matching vertices in two correlated Erd\H{o}s-R\'enyi graphs, we study the problem of matching two correlated Gaussian Wigner matrices. We propose an iterative matching algorithm, which succeeds in polynomial time as long as the correlation between the two Gaussian matrices does not vanish. Our result is the first polynomial time algorithm that solves a graph matching type of problem when the correlation is an arbitrarily small constant.
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 $的阈值都会很清晰。最后,我们得出了近似奇异向量的行波和近似矩阵的进入波动的正常近似。我们通过将RSVD的几乎最佳性能保证在应用于三个统计推断问题的情况下,即社区检测,矩阵完成和主要的组件分析,并使用缺失的数据来说明我们的理论结果。
translated by 谷歌翻译
我们调查与高斯的混合的数据分享共同但未知,潜在虐待协方差矩阵的数据。我们首先考虑具有两个等级大小的组件的高斯混合,并根据最大似然估计导出最大切割整数程序。当样品的数量在维度下线性增长时,我们证明其解决方案实现了最佳的错误分类率,直到对数因子。但是,解决最大切割问题似乎是在计算上棘手的。为了克服这一点,我们开发了一种高效的频谱算法,该算法达到最佳速率,但需要一种二次样本量。虽然这种样本复杂性比最大切割问题更差,但我们猜测没有多项式方法可以更好地执行。此外,我们收集了支持统计计算差距存在的数值和理论证据。最后,我们将MAX-CUT程序概括为$ k $ -means程序,该程序处理多组分混合物的可能性不平等。它享有相似的最优性保证,用于满足运输成本不平等的分布式的混合物,包括高斯和强烈的对数的分布。
translated by 谷歌翻译
Given a symmetric matrix $M$ and a vector $\lambda$, we present new bounds on the Frobenius-distance utility of the Gaussian mechanism for approximating $M$ by a matrix whose spectrum is $\lambda$, under $(\varepsilon,\delta)$-differential privacy. Our bounds depend on both $\lambda$ and the gaps in the eigenvalues of $M$, and hold whenever the top $k+1$ eigenvalues of $M$ have sufficiently large gaps. When applied to the problems of private rank-$k$ covariance matrix approximation and subspace recovery, our bounds yield improvements over previous bounds. Our bounds are obtained by viewing the addition of Gaussian noise as a continuous-time matrix Brownian motion. This viewpoint allows us to track the evolution of eigenvalues and eigenvectors of the matrix, which are governed by stochastic differential equations discovered by Dyson. These equations allow us to bound the utility as the square-root of a sum-of-squares of perturbations to the eigenvectors, as opposed to a sum of perturbation bounds obtained via Davis-Kahan-type theorems.
translated by 谷歌翻译
This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models-including Gaussian mixture models, hidden Markov models, and latent Dirichlet allocation-which exploits a certain tensor structure in their low-order observable moments (typically, of second-and third-order). Specifically, parameter estimation is reduced to the problem of extracting a certain (orthogonal) decomposition of a symmetric tensor derived from the moments; this decomposition can be viewed as a natural generalization of the singular value decomposition for matrices. Although tensor decompositions are generally intractable to compute, the decomposition of these specially structured tensors can be efficiently obtained by a variety of approaches, including power iterations and maximization approaches (similar to the case of matrices). A detailed analysis of a robust tensor power method is provided, establishing an analogue of Wedin's perturbation theorem for the singular vectors of matrices. This implies a robust and computationally tractable estimation approach for several popular latent variable models.
translated by 谷歌翻译
近似消息传递(AMP)是解决高维统计问题的有效迭代范式。但是,当迭代次数超过$ o \ big(\ frac {\ log n} {\ log log \ log \ log n} \时big)$(带有$ n $问题维度)。为了解决这一不足,本文开发了一个非吸附框架,用于理解峰值矩阵估计中的AMP。基于AMP更新的新分解和可控的残差项,我们布置了一个分析配方,以表征在存在独立初始化的情况下AMP的有限样本行为,该过程被进一步概括以进行光谱初始化。作为提出的分析配方的两个具体后果:(i)求解$ \ mathbb {z} _2 $同步时,我们预测了频谱初始化AMP的行为,最高为$ o \ big(\ frac {n} {\ mathrm {\ mathrm { poly} \ log n} \ big)$迭代,表明该算法成功而无需随后的细化阶段(如最近由\ citet {celentano2021local}推测); (ii)我们表征了稀疏PCA中AMP的非反应性行为(在尖刺的Wigner模型中),以广泛的信噪比。
translated by 谷歌翻译
社区检测是网络科学中的一个基本问题。在本文中,我们考虑了从$ HyperGraph $ $ $ $ $ $ $ $ $ $ $ $ $ $ $(HSBM)中绘制的HyperGraphs中的社区检测,重点是精确的社区恢复。在整个超图未知的情况下,我们研究了多项式时间算法以进行社区检测的性能。取而代之的是,我们获得了$相似性$ $ $ $ $ $ $ w $,其中$ w_ {ij} $报告包含$ i $和$ j $的超补品的数量。在此信息模型下,Kim,Bandeira和Goemans [KBG18]确定了信息理论阈值,以进行精确恢复,并提出了他们认为是最佳的半决赛编程松弛。在本文中,我们确认了这个猜想。我们还表明,一种简单,高效的光谱算法是最佳的,将光谱算法作为选择方法。我们对光谱算法的分析至关重要地依赖于$ w $的特征向量上的强$ entrywise $界限。我们的边界灵感来自Abbe,Fan,Wang和Zhong [AFWZ20]的工作,他们开发了具有独立条目的对称矩阵的特征向量的进入界。尽管相似性矩阵的依赖性结构复杂,但我们证明了相似的入口保证。
translated by 谷歌翻译
We consider a problem of considerable practical interest: the recovery of a data matrix from a sampling of its entries. Suppose that we observe m entries selected uniformly at random from a matrix M . Can we complete the matrix and recover the entries that we have not seen?We show that one can perfectly recover most low-rank matrices from what appears to be an incomplete set of entries. We prove that if the number m of sampled entries obeys m ≥ C n 1.2 r log n for some positive numerical constant C, then with very high probability, most n × n matrices of rank r can be perfectly recovered by solving a simple convex optimization program. This program finds the matrix with minimum nuclear norm that fits the data. The condition above assumes that the rank is not too large. However, if one replaces the 1.2 exponent with 1.25, then the result holds for all values of the rank. Similar results hold for arbitrary rectangular matrices as well. Our results are connected with the recent literature on compressed sensing, and show that objects other than signals and images can be perfectly reconstructed from very limited information.
translated by 谷歌翻译
特征向量扰动分析在各种数据科学应用中起着至关重要的作用。然而,大量的先前作品着重于建立$ \ ell_ {2} $ eigenVector扰动边界,这些范围通常在解决依赖特征向量的细粒度行为的任务方面非常不足。本文通过研究未知特征向量的线性函数的扰动来取得进展。在存在高斯噪声的情况下,着重于两个基本问题 - 矩阵denoising和主成分分析 - 我们开发了一个统计理论的套件,该理论表征了未知特征向量的任意线性函数的扰动。为了减轻自然``插件''估计器固有的不可忽略的偏见问题,我们开发了偏低的估计器,即(1)(1)为场景家庭实现最小的下限(模仿某些对数因素),并且(2)可以以数据驱动的方式计算,而无需样品分裂。值得注意的是,即使相关的特征间隙{\ em少于先前的统计理论所要求的,提出的估计器几乎是最佳的最佳选择。
translated by 谷歌翻译
我们考虑在排名一的尖刺模型中检测信号的存在的问题。对于一般的非高斯噪声,假设信号是从rademacher先验中汲取的,我们证明,当信号噪声比率低于信号噪声时,尖峰模型的对数可能性比(LR)收敛到高斯一定的阈值。阈值是最佳的,因为在其上方,可以通过转换的主组件分析(PCA)进行可靠的检测。从对数LR的限制高斯的平均值和方差,我们计算了I型误差之和的限制以及似然比测试的类型II误差。对于噪声不对称,但信号是对称的,我们还证明了一个排名一的尖峰IID模型的结果相似。
translated by 谷歌翻译
In this work, we give efficient algorithms for privately estimating a Gaussian distribution in both pure and approximate differential privacy (DP) models with optimal dependence on the dimension in the sample complexity. In the pure DP setting, we give an efficient algorithm that estimates an unknown $d$-dimensional Gaussian distribution up to an arbitrary tiny total variation error using $\widetilde{O}(d^2 \log \kappa)$ samples while tolerating a constant fraction of adversarial outliers. Here, $\kappa$ is the condition number of the target covariance matrix. The sample bound matches best non-private estimators in the dependence on the dimension (up to a polylogarithmic factor). We prove a new lower bound on differentially private covariance estimation to show that the dependence on the condition number $\kappa$ in the above sample bound is also tight. Prior to our work, only identifiability results (yielding inefficient super-polynomial time algorithms) were known for the problem. In the approximate DP setting, we give an efficient algorithm to estimate an unknown Gaussian distribution up to an arbitrarily tiny total variation error using $\widetilde{O}(d^2)$ samples while tolerating a constant fraction of adversarial outliers. Prior to our work, all efficient approximate DP algorithms incurred a super-quadratic sample cost or were not outlier-robust. For the special case of mean estimation, our algorithm achieves the optimal sample complexity of $\widetilde O(d)$, improving on a $\widetilde O(d^{1.5})$ bound from prior work. Our pure DP algorithm relies on a recursive private preconditioning subroutine that utilizes the recent work on private mean estimation [Hopkins et al., 2022]. Our approximate DP algorithms are based on a substantial upgrade of the method of stabilizing convex relaxations introduced in [Kothari et al., 2022].
translated by 谷歌翻译
在这项工作中,我们研究了随机特征矩阵$ m = yy ^ \ ast $的渐近光谱密度用一个单独的层神经网络生成的$ y = f(wx)$,其中$ w $和$ x $是带有IID的随机矩形矩阵中心条目和$ F $是一种非线性光滑功能,其应用进入明智。我们证明了限制光谱分布的Stieltjes转换大致满足四个自我一致的等式,这正是通过[Pennityton,Worah]和[Benigni,P \'E]获得的等式。我们将以前的结果扩展到附加偏见$ Y = F(WX + B)$的情况下,以$ B $为一个独立的秩 - 一个高斯随机矩阵,更接近实践中遇到的神经网络基础架构。我们的主要发现是,在添加剂偏差的情况下,不可能选择保持层到层奇异值分布的激活函数,与无偏置的情况鲜明对比,其中简单的积分约束足以实现非偏光曲线。为了获得经验谱密度的渐近学,我们通过累积扩展来遵循从随机矩阵理论的解析方法。我们发现这种方法比瞬间方法更强大,而且组合较少,并期望它也适用于前者的组合物变得棘手的模型。已经广泛采用了解析方法,但与以前的作品相比,这里应用于非线性随机矩阵。
translated by 谷歌翻译
张量模型在许多领域中起着越来越重要的作用,特别是在机器学习中。在几种应用中,例如社区检测,主题建模和高斯混合物学习,必须估算噪声张量的低级别信号。因此,了解该信号的估计器的基本限制不可避免地要求研究随机张量。最近,在大维限制中,该主题取得了实质性进展。然而,其中一些最重要的结果(尤其是对突然的相变(相对于信噪比)的精确表征),该表现控制着对称等级的最大可能性(ML)估计器的性能 - 具有高斯噪声的模型 - 基于平均场自旋玻璃理论得出,非专家不容易访问。在这项工作中,我们依靠标准但强大的工具开发出一种截然不同,更基本的方法,这是由随机矩阵理论的多年进步带来的。关键思想是研究由给定随机张量的收缩引起的随机矩阵的光谱。我们展示了如何访问随机张量本身的光谱属性。对于上述排名衡量模型,我们的技术产生了迄今未知的固定点方程,其解决方案与第三阶情况下的相变阈值高于相变阈值的ML估计器的渐近性能。数值验证提供了证据,表明订单4和5相同,导致我们猜想,对于任何顺序,我们的定点方程等于已知的ML估计性能的表征,这些表现通过依靠旋转玻璃而获得。此外,我们的方法阐明了ML问题景观的某些特性,可以扩展到其他模型,例如不对称和非高斯。
translated by 谷歌翻译
Consider the problem of matching two independent i.i.d. samples of size $N$ from two distributions $P$ and $Q$ in $\mathbb{R}^d$. For an arbitrary continuous cost function, the optimal assignment problem looks for the matching that minimizes the total cost. We consider instead in this paper the problem where each matching is endowed with a Gibbs probability weight proportional to the exponential of the negative total cost of that matching. Viewing each matching as a joint distribution with $N$ atoms, we then take a convex combination with respect to the above Gibbs probability measure. We show that this resulting random joint distribution converges, as $N\rightarrow \infty$, to the solution of a variational problem, introduced by F\"ollmer, called the Schr\"odinger problem. We also derive the first two error terms of orders $N^{-1/2}$ and $N^{-1}$, respectively. This gives us central limit theorems for integrated test functions, including for the cost of transport, and second order Gaussian chaos limits when the limiting Gaussian variance is zero. The proofs are based on a novel chaos decomposition of the discrete Schr\"odinger bridge by polynomial functions of the pair of empirical distributions as the first and second order Taylor approximations in the space of measures. This is achieved by extending the Hoeffding decomposition from the classical theory of U-statistics.
translated by 谷歌翻译
高维统计数据的一个基本目标是检测或恢复嘈杂数据中隐藏的种植结构(例如低级别矩阵)。越来越多的工作研究低级多项式作为此类问题的计算模型的限制模型:在各种情况下,数据的低级多项式可以与最知名的多项式时间算法的统计性能相匹配。先前的工作已经研究了低度多项式的力量,以检测隐藏结构的存在。在这项工作中,我们将这些方法扩展到解决估计和恢复问题(而不是检测)。对于大量的“信号加噪声”问题,我们给出了一个用户友好的下限,以获得最佳的均衡误差。据我们所知,这些是建立相关检测问题的恢复问题低度硬度的第一个结果。作为应用,我们对种植的子静脉和种植的密集子图问题的低度最小平方误差进行了严格的特征,在两种情况下都解决了有关恢复的计算复杂性的开放问题(在低度框架中)。
translated by 谷歌翻译
我们重新审视量子状态认证的基本问题:给定混合状态$ \ rho \中的副本\ mathbb {c} ^ {d \ times d} $和混合状态$ \ sigma $的描述,决定是否$ \ sigma = \ rho $或$ \ | \ sigma - \ rho \ | _ {\ mathsf {tr}} \ ge \ epsilon $。当$ \ sigma $最大化时,这是混合性测试,众所周知,$ \ omega(d ^ {\ theta(1)} / \ epsilon ^ 2)$副本是必要的,所以确切的指数取决于测量类型学习者可以使[OW15,BCL20],并且在许多这些设置中,有一个匹配的上限[OW15,Bow19,BCL20]。可以避免这种$ d ^ {\ theta(1)} $依赖于某些类型的混合状态$ \ sigma $,例如。大约低等级的人?更常见地,是否存在一个简单的功能$ f:\ mathbb {c} ^ {d \ times d} \ to \ mathbb {r} _ {\ ge 0} $,其中一个人可以显示$ \ theta(f( \ sigma)/ \ epsilon ^ 2)$副本是必要的,并且足以就任何$ \ sigma $的国家认证?这种实例 - 最佳边界在经典分布测试的背景下是已知的,例如, [VV17]。在这里,我们为量子设置提供了这个性质的第一个界限,显示(达到日志因子),即使用非接受不连贯测量的状态认证的复杂性复杂性基本上是通过复制复杂性进行诸如$ \ sigma $之间的保真度的复杂性。和最大混合的状态。令人惊讶的是,我们的界限与经典问题的实例基本上不同,展示了两个设置之间的定性差异。
translated by 谷歌翻译