arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.03086math.STmath.PRstat.MLstat.TH
收藏

重尾分布的仿射不变协方差估计

Affine Invariant Covariance Estimation for Heavy-Tailed Distributions

Dmitrii Ostrovskii, Alessandro Rudi

摘要:

本文给出了重尾多元分布协方差阵的一个估计,证明了估计$\widehat{\mathbf{S}}$在高概率下存在形式为\[(1-\varepsilon) \mathbf{S} \preccurlyeq \widehat{\mathbf{S}} \preccurlyeq (1+\varepsilon) \mathbf{S}\]的\textit{affine-invariant}界,其中$\mathbf{S}$是未知协方差阵,$\preccurlyeq$是对称矩阵的半正定阶.结果只需要存在四阶矩,并允许$\varepsilon = O(\sqrt{κ^4 d\log(d/δ)/n})$,其中$κ^4$是分布峰度的度量,$d$是空间的维数,$n$是样本量,$1-δ$是期望的置信水平。更一般地说,我们可以允许使用$λ$级别进行正则化,然后$d$被自由度数取代。用$\text{cond}(\mathbf{S})$表示$\mathbf{S}$的条件数,新估计量的计算量为$O(d^2 n + d^3\log(\text{cond}(\mathbf{S})))$,与统计意义下的样本协方差估计量$n \ge d$的计算量相当.我们考虑我们的估计的应用程序的特征值估计的相对误差,和岭回归重尾随机设计。

英文摘要:

In this work we provide an estimator for the covariance matrix of a heavy-tailed multivariate distributionWe prove that the proposed estimator $\widehat{\mathbf{S}}$ admits an \textit{affine-invariant} bound of the form \[(1-\varepsilon) \mathbf{S} \preccurlyeq \widehat{\mathbf{S}} \preccurlyeq (1+\varepsilon) \mathbf{S}\]in high probability, where $\mathbf{S}$ is the unknown covariance matrix, and $\preccurlyeq$ is the positive semidefinite order on symmetric matrices. The result only requires the existence of fourth-order moments, and allows for $\varepsilon = O(\sqrt{κ^4 d\log(d/δ)/n})$ where $κ^4$ is a measure of kurtosis of the distribution, $d$ is the dimensionality of the space, $n$ is the sample size, and $1-δ$ is the desired confidence level. More generally, we can allow for regularization with level $λ$, then $d$ gets replaced with the degrees of freedom number. Denoting $\text{cond}(\mathbf{S})$ the condition number of $\mathbf{S}$, the computational cost of the novel estimator is $O(d^2 n + d^3\log(\text{cond}(\mathbf{S})))$, which is comparable to the cost of the sample covariance estimator in the statistically interesing regime $n \ge d$. We consider applications of our estimator to eigenvalue estimation with relative error, and to ridge regression with heavy-tailed random design.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑