Tyler's and Maronna's M-estimators, as well as their regularized variants, are popular robust methods to estimate the scatter or covariance matrix of a multivariate distribution. In this work, we study the non-asymptotic behavior of these estimators, for data sampled from a distribution that satisfies one of the following properties: 1) independent sub-Gaussian entries, up to a linear transformation; 2) log-concave distributions; 3) distributions satisfying a convex concentration property. Our main contribution is the derivation of tight non-asymptotic concentration bounds of these M-estimators around a suitably scaled version of the data sample covariance matrix. Prior to our work, non-asymptotic bounds were derived only for Elliptical and Gaussian distributions. Our proof uses a variety of tools from non asymptotic random matrix theory and high dimensional geometry. Finally, we illustrate the utility of our results on two examples of practical interest: sparse covariance and sparse precision matrix estimation.
翻译:Tyler 和 Maronna 的 M 估计器及其常规化变体是用来估计多变量分布的散射或共变矩阵的常用的可靠方法。 在这项工作中,我们研究这些估计器的非非无损行为,以便从符合以下特性之一的分布中抽样数据:1) 独立的亚伽鲁西安条目,直至线性变换;2) 日志混凝土分布;3) 能够满足 convex 集中特性的分布。我们的主要贡献是在数据样本变异矩阵的合适缩放版本周围推断出这些测算器的紧凑非无损浓度界限。 在我们工作之前,非无损界限仅用于 Elliptical 和 Gaussian 分布。我们的证据使用了多种工具,包括非非随机矩阵理论和高维度几何测量。 最后,我们用两个实例来说明我们的结果的实用价值: 很少的可调和稀少精确矩阵估计。