arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1503.01245math.STcs.ITmath.ITstat.MLstat.TH
收藏

异常值协方差稳健M-估计的高维分析

Large Dimensional Analysis of Robust M-Estimators of Covariance with Outliers

David Morales-Jimenez, Romain Couillet, Matthew R. McKay

摘要:

假设数据集包括独立的(本质上是高斯的)合法样本以及任意确定性样本(称为离群值),提供了协方差(或散布)的鲁棒M-估计量的高维特征。建立在最近的随机矩阵的鲁棒统计领域的进展,我们特别表明,所谓的Maronna M-估计的散布渐近行为类似于众所周知的随机矩阵时,人口和样本量一起增长到无穷大。离群值的引入使得鲁棒估计渐近地表现为样本外积的加权和,对于所有合法样本具有恒定的权重,而对于离群值具有不同的权重。对这种结构的精细分析揭示了重要的是,M估计量衰减(或增强)离群值影响的倾向主要取决于离群值与合法样本的逆总体协方差阵的对齐。因此,鲁棒M-估计量可以带来实质性的好处,更简单的估计,如每样本归一化版本的样本协方差阵,这是不能够区分离群样本。分析表明,在一类的Maronna的估计的散布,Huber估计是最有利的拒绝离群值。相反,更类似于泰勒尺度不变估计量的估计量(通常在文献中更受欢迎)有可能无意中增强一些离群值。

英文摘要:

A large dimensional characterization of robust M-estimators of covariance (or scatter) is provided under the assumption that the dataset comprises independent (essentially Gaussian) legitimate samples as well as arbitrary deterministic samples, referred to as outliers. Building upon recent random matrix advances in the area of robust statistics, we specifically show that the so-called Maronna M-estimator of scatter asymptotically behaves similar to well-known random matrices when the population and sample sizes grow together to infinity. The introduction of outliers leads the robust estimator to behave asymptotically as the weighted sum of the sample outer products, with a constant weight for all legitimate samples and different weights for the outliers. A fine analysis of this structure reveals importantly that the propensity of the M-estimator to attenuate (or enhance) the impact of outliers is mostly dictated by the alignment of the outliers with the inverse population covariance matrix of the legitimate samples. Thus, robust M-estimators can bring substantial benefits over more simplistic estimators such as the per-sample normalized version of the sample covariance matrix, which is not capable of differentiating the outlying samples. The analysis shows that, within the class of Maronna's estimators of scatter, the Huber estimator is most favorable for rejecting outliers. On the contrary, estimators more similar to Tyler's scale invariant estimator (often preferred in the literature) run the risk of inadvertently enhancing some outliers.

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。

↑