我们重新访问重尾损坏的最小二乘线性回归,假设最多损坏了$ n $ n $ n $ sized的标签 - 功能样本,最多是$ \ epsilon n $ nutialary Outliers。我们希望估计给定标签 - 功能对$(y,x)$满足$ y = \ y = \ langle x,b^*\ rangle+xi $的标签 - 功能对$(y,x)$的样本给定$ p $ -dimensional参数$ b^*$ - 尾$(x,\ xi)$。我们只假设$ x $ is $ l^4-l^2 $超债券与常数$ l> 0 $,并具有协方差矩阵$ \ sigma $,最低eigenvalue $ 1/\ mu^2> 0 $和有限条件号$ \ \ \ \ \ \ \ \ kappa> 0 $。只要$ \ xi x $具有有限的协方差矩阵$ \ xi $,噪声$ \ xi $可以任意取决于$ x $,而非对称性。我们提出了一个基于功率方法的近乎最佳的计算估计器,假设对$(\ sigma,\ xi)$也不了解$ \ xi $的运算符规范。如果概率至少$ 1- \ delta $,我们提出的估计器达到了统计率$ \ mu^2 \ vert \ xi \ xi \ vert^{1/2}(\ frac {p} {n} {n}+\ frac {\ log(\ log(\ log( 1/\ delta)}} {n}+\ epsilon)^{1/2} $ and beckdown-point $ \ epsilon \ epsilon \ sillesim \ frac {1} {l^4 \ kappa^2} $ \ ell_2 $ - norm,假设最小最小样本大小$ l^4 \ kappa^2(p \ log p + p + \ log(1/\ delta))\ sillsim n $,最多为log fix因数。据我们所知,这是同时满足所有提到的所有属性的第一个计算障碍算法。我们的估计器基于两阶段的乘量重量更新算法。第一阶段估计了(未知)预先条件的内部产品$ \ langle \ sigma(\ cdot),\ cdot \ rangle $。第二阶段估计下降方向$ \ sigma \ hat v $相对于(已知的)内部产品$ \ langle \ cdot,\ cdot \ rangle $,而无需了解或估计$ \ sigma $。
translated by 谷歌翻译
We study the fundamental task of outlier-robust mean estimation for heavy-tailed distributions in the presence of sparsity. Specifically, given a small number of corrupted samples from a high-dimensional heavy-tailed distribution whose mean $\mu$ is guaranteed to be sparse, the goal is to efficiently compute a hypothesis that accurately approximates $\mu$ with high probability. Prior work had obtained efficient algorithms for robust sparse mean estimation of light-tailed distributions. In this work, we give the first sample-efficient and polynomial-time robust sparse mean estimator for heavy-tailed distributions under mild moment assumptions. Our algorithm achieves the optimal asymptotic error using a number of samples scaling logarithmically with the ambient dimension. Importantly, the sample complexity of our method is optimal as a function of the failure probability $\tau$, having an additive $\log(1/\tau)$ dependence. Our algorithm leverages the stability-based approach from the algorithmic robust statistics literature, with crucial (and necessary) adaptations required in our setting. Our analysis may be of independent interest, involving the delicate design of a (non-spectral) decomposition for positive semi-definite matrices satisfying certain sparsity properties.
translated by 谷歌翻译
我们研究了在存在$ \ epsilon $ - 对抗异常值的高维稀疏平均值估计的问题。先前的工作为此任务获得了该任务的样本和计算有效算法,用于辅助性Subgaussian分布。在这项工作中,我们开发了第一个有效的算法,用于强大的稀疏平均值估计,而没有对协方差的先验知识。对于$ \ Mathbb r^d $上的分布,带有“认证有限”的$ t $ tum-矩和足够轻的尾巴,我们的算法达到了$ o(\ epsilon^{1-1/t})$带有样品复杂性$的错误(\ epsilon^{1-1/t}) m =(k \ log(d))^{o(t)}/\ epsilon^{2-2/t} $。对于高斯分布的特殊情况,我们的算法达到了$ \ tilde o(\ epsilon)$的接近最佳错误,带有样品复杂性$ m = o(k^4 \ mathrm {polylog}(d)(d))/\ epsilon^^ 2 $。我们的算法遵循基于方形的总和,对算法方法的证明。我们通过统计查询和低度多项式测试的下限来补充上限,提供了证据,表明我们算法实现的样本时间 - 错误权衡在质量上是最好的。
translated by 谷歌翻译
我们介绍了一个普遍的框架,用于表征差异隐私保证的统计估算问题的统计效率。我们的框架,我们呼叫高维建议 - 试验释放(HPTR),在三个重要组件上建立:指数机制,强大的统计和提议 - 试验释放机制。将所有这些粘在一起是恢复力的概念,这是强大的统计估计的核心。弹性指导算法的设计,灵敏度分析和试验步骤的成功概率分析。关键识别是,如果我们设计了一种仅通过一维鲁棒统计数据访问数据的指数机制,则可以大大减少所产生的本地灵敏度。使用弹性,我们可以提供紧密的本地敏感界限。这些紧张界限在几个案例中容易转化为近乎最佳的实用程序。我们给出了将HPTR应用于统计估计问题的给定实例的一般配方,并在平均估计,线性回归,协方差估计和主成分分析的规范问题上证明了它。我们介绍了一般的公用事业分析技术,证明了HPTR几乎在文献中研究的若干场景下实现了最佳的样本复杂性。
translated by 谷歌翻译
我们给出了\ emph {list-codobable协方差估计}的第一个多项式时间算法。对于任何$ \ alpha> 0 $,我们的算法获取输入样本$ y \ subseteq \ subseteq \ mathbb {r}^d $ size $ n \ geq d^{\ mathsf {poly}(1/\ alpha)} $获得通过对抗损坏I.I.D的$(1- \ alpha)n $点。从高斯分布中的样本$ x $ size $ n $,其未知平均值$ \ mu _*$和协方差$ \ sigma _*$。在$ n^{\ mathsf {poly}(1/\ alpha)} $ time中,它输出$ k = k(\ alpha)=(1/\ alpha)^{\ mathsf {poly}的常数大小列表(1/\ alpha)} $候选参数,具有高概率,包含$(\ hat {\ mu},\ hat {\ sigma})$,使得总变化距离$ tv(\ Mathcal {n}(n})(n}(n})( \ mu _*,\ sigma _*),\ Mathcal {n}(\ hat {\ mu},\ hat {\ sigma}))<1-o _ {\ alpha}(1)$。这是距离的统计上最强的概念,意味着具有独立尺寸误差的参数的乘法光谱和相对Frobenius距离近似。我们的算法更普遍地适用于$(1- \ alpha)$ - 任何具有低度平方总和证书的分布$ d $的损坏,这是两个自然分析属性的:1)一维边际和抗浓度2)2度多项式的超收缩率。在我们工作之前,估计可定性设置的协方差的唯一已知结果是针对Karmarkar,Klivans和Kothari(2019),Raghavendra和Yau(2019和2019和2019和2019和2019年)的特殊情况。 2020年)和巴克西(Bakshi)和科塔里(Kothari)(2020年)。这些结果需要超级物理时间,以在基础维度中获得任何子构误差。我们的结果意味着第一个多项式\ emph {extcect}算法,用于列表可解码的线性回归和子空间恢复,尤其允许获得$ 2^{ - \ Mathsf { - \ Mathsf {poly}(d)} $多项式时间错误。我们的结果还意味着改进了用于聚类非球体混合物的算法。
translated by 谷歌翻译
我们在高维批处理设置中提出了统计上健壮和计算高效的线性学习方法,其中功能$ d $的数量可能超过样本量$ n $。在通用学习环境中,我们采用两种算法,具体取决于所考虑的损失函数是否为梯度lipschitz。然后,我们将我们的框架实例化,包括几种应用程序,包括香草稀疏,群 - 帕克斯和低升级矩阵恢复。对于每种应用,这导致了有效而强大的学习算法,这些算法在重尾分布和异常值的存在下达到了近乎最佳的估计率。对于香草$ S $ -SPARSITY,我们能够以重型尾巴和$ \ eta $ - 腐败的计算成本与非企业类似物相当的计算成本达到$ s \ log(d)/n $速率。我们通过开放源代码$ \ mathtt {python} $库提供了有效的算法实现文献中提出的最新方法。
translated by 谷歌翻译
We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to robustness which can produce private estimators with optimal tradeoffs among sample complexity, accuracy, and privacy for a wide range of fundamental high-dimensional parameter estimation problems, including mean and covariance estimation. We show that this reduction can be implemented in polynomial time in some important special cases. In particular, using nearly-optimal polynomial-time robust estimators for the mean and covariance of high-dimensional Gaussians which are based on the Sum-of-Squares method, we design the first polynomial-time private estimators for these problems with nearly-optimal samples-accuracy-privacy tradeoffs. Our algorithms are also robust to a constant fraction of adversarially-corrupted samples.
translated by 谷歌翻译
当分别从$ \ mathfrak {l} $ - subgaussian分布和重尾分布中,分别采样协变量和噪声时,我们考虑了线性回归系数的鲁棒和稀疏估计,并由对抗性和噪音污染异常值。我们处理两种情况:协变量的已知或未知协方差。特别是在前一种情况下,我们的估计器几乎达到了信息理论上的最佳错误绑定,而我们的错误界限比以前处理类似情况的研究更明显。我们的估计分析在很大程度上依赖于通用链条来得出急剧的误差界限。
translated by 谷歌翻译
Testing the significance of a variable or group of variables $X$ for predicting a response $Y$, given additional covariates $Z$, is a ubiquitous task in statistics. A simple but common approach is to specify a linear model, and then test whether the regression coefficient for $X$ is non-zero. However, when the model is misspecified, the test may have poor power, for example when $X$ is involved in complex interactions, or lead to many false rejections. In this work we study the problem of testing the model-free null of conditional mean independence, i.e. that the conditional mean of $Y$ given $X$ and $Z$ does not depend on $X$. We propose a simple and general framework that can leverage flexible nonparametric or machine learning methods, such as additive models or random forests, to yield both robust error control and high power. The procedure involves using these methods to perform regressions, first to estimate a form of projection of $Y$ on $X$ and $Z$ using one half of the data, and then to estimate the expected conditional covariance between this projection and $Y$ on the remaining half of the data. While the approach is general, we show that a version of our procedure using spline regression achieves what we show is the minimax optimal rate in this nonparametric testing problem. Numerical experiments demonstrate the effectiveness of our approach both in terms of maintaining Type I error control, and power, compared to several existing approaches.
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
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
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
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
我们提供匹配的Under $ \ sigma ^ 2 / \ log(d / n)$的匹配的上下界限为最低$ \ ell_1 $ -norm插值器,a.k.a.基础追踪。我们的结果紧紧达到可忽略的术语,而且是第一个暗示噪声最小范围内插值的渐近一致性,因为各向同性特征和稀疏的地面真理。我们的工作对最低$ \ ell_2 $ -norm插值的“良性接收”进行了补充文献,其中才能在特征有效地低维时实现渐近一致性。
translated by 谷歌翻译
本文为信号去噪提供了一般交叉验证框架。然后将一般框架应用于非参数回归方法,例如趋势过滤和二元推车。然后显示所得到的交叉验证版本以获得最佳调谐的类似物所熟知的几乎相同的收敛速度。没有任何先前的趋势过滤或二元推车的理论分析。为了说明框架的一般性,我们还提出并研究了两个基本估算器的交叉验证版本;套索用于高维线性回归和矩阵估计的奇异值阈值阈值。我们的一般框架是由Chatterjee和Jafarov(2015)的想法的启发,并且可能适用于使用调整参数的广泛估算方法。
translated by 谷歌翻译
我们研究了清单可解放的平均估计问题,而对手可能会破坏大多数数据集。具体来说,我们在$ \ mathbb {r} ^ $和参数$ 0 <\ alpha <\ frac 1 2 $中给出了一个$ $ n $ points的$ t $ points。$ \ alpha $ -flaction的点$ t $是iid来自乖巧的分发$ \ Mathcal {D} $的样本,剩余的$(1- \ alpha)$ - 分数是任意的。目标是输出小型的vectors列表,其中至少一个接近$ \ mathcal {d} $的均值。我们开发新的算法,用于列出可解码的平均值估计,实现几乎最佳的统计保证,运行时间$ O(n ^ {1 + \ epsilon_0} d)$,适用于任何固定$ \ epsilon_0> 0 $。所有先前的此问题算法都有额外的多项式因素在$ \ frac 1 \ alpha $。我们与额外技术一起利用此结果,以获得用于聚类混合物的第一个近几个线性时间算法,用于分开的良好表现良好的分布,几乎匹配谱方法的统计保证。先前的聚类算法本身依赖于$ k $ -pca的应用程序,从而产生$ \ omega(n d k)$的运行时。这标志着近二十年来这个基本统计问题的第一次运行时间改进。我们的方法的起点是基于单次矩阵乘法权重激发电位减少的$ \ Alpha \至1 $制度中的新颖和更简单的近线性时间较强的估计算法。在Diakonikolas等人的迭代多滤波技术的背景下,我们迫切地利用了这种新的算法框架。 '18,'20,提供一种使用一维投影的同时群集和下群点的方法 - 因此,绕过先前算法所需的$ k $ -pca子程序。
translated by 谷歌翻译
本文研究了具有对抗性误差的强大一位压缩感应的二进制分类。假设该模型过度分配,并且感兴趣的参数有效稀疏。adaboost被考虑,并且通过其与MAX - $ \ ell_1 $ -Margin-Scressifir的关系,派生预测错误界限。开发的理论是一般的,并且允许重型的特征分布,只需要一个薄弱的时刻假设和抗浓缩条件。当特征满足小偏差下限时,示出了改善的收敛速率。特别是,结果提供了解释为什么内插对抗性噪声对于分类问题可以是无害的。模拟说明了所提出的理论。
translated by 谷歌翻译
素描的Wasserstein距离($ W^S $)是专门针对有限混合物分布的新概率距离。给定概率分布的集合$ \ MATHCAL {a} $定义的任何度量$ d $,$ w^s $定义为该指标的最判别凸扩展为space $ \ mathcal {s} = \ textrm {cons}(\ Mathcal {a})$ \ Mathcal {a} $的元素混合物的$。我们的表示定理表明,以这种方式构建的空间$(\ MATHCAL {S},w^s)$对$ \ MATHCAL {x} =(\ Mathcal {a},d)$的wasserstein空间是同构的。该结果为Wasserstein距离建立了普遍性,表明它们的特征是它们具有有限混合物的判别能力。我们利用此表示定理提出了基于Kantorovich--Rubenstein二元性的估计方法,并证明了一般定理,该定理表明其估计误差可以由任何估计混合物重量和混合物组件的误差的总和来限制。这些数量的估计器。在$ p $二维离散$ k $ -mixtures的情况下,我们得出了估计$ w^s $的尖锐统计属性,我们显示的可以估计的速率与$ \ sqrt {k/n} $,达到对数因素。我们对这些边界进行了互补,以估计$ k $ - 点度量空间上的分布之间的瓦斯汀距离的风险,这与我们的上限与对数因素相匹配。该结果是用于估计离散分布之间的Wasserstein距离的第一个接近最小的下限。此外,我们构造了混合物权重的$ \ sqrt {n} $渐变正常的估计器,并得出了我们$ w^s $的估计器的$ \ sqrt {n} $分布限制。仿真研究和数据分析为新素描的瓦斯汀距离的适用性提供了强有力的支持。
translated by 谷歌翻译
在共享数据的统计学习和分析中,在联合学习和元学习等平台上越来越广泛地采用,有两个主要问题:隐私和鲁棒性。每个参与的个人都应该能够贡献,而不会担心泄露一个人的敏感信息。与此同时,系统应该在恶意参与者的存在中插入损坏的数据。最近的算法在学习中,学习共享数据专注于这些威胁中的一个,使系统容易受到另一个威胁。我们弥合了这个差距,以获得估计意思的规范问题。样品。我们介绍了素数,这是第一算法,实现了各种分布的隐私和鲁棒性。我们通过新颖的指数时间算法进一步补充了这一结果,提高了素数的样本复杂性,实现了近最优保证并匹配(非鲁棒)私有平均估计的已知下限。这证明没有额外的统计成本同时保证隐私和稳健性。
translated by 谷歌翻译
Popular iterative algorithms such as boosting methods and coordinate descent on linear models converge to the maximum $\ell_1$-margin classifier, a.k.a. sparse hard-margin SVM, in high dimensional regimes where the data is linearly separable. Previous works consistently show that many estimators relying on the $\ell_1$-norm achieve improved statistical rates for hard sparse ground truths. We show that surprisingly, this adaptivity does not apply to the maximum $\ell_1$-margin classifier for a standard discriminative setting. In particular, for the noiseless setting, we prove tight upper and lower bounds for the prediction error that match existing rates of order $\frac{\|\wgt\|_1^{2/3}}{n^{1/3}}$ for general ground truths. To complete the picture, we show that when interpolating noisy observations, the error vanishes at a rate of order $\frac{1}{\sqrt{\log(d/n)}}$. We are therefore first to show benign overfitting for the maximum $\ell_1$-margin classifier.
translated by 谷歌翻译