arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.02880math.STstat.TH
收藏

协方差矩阵的鲁棒估计:对抗污染及其他场景

Robust Estimation of Covariance Matrices: Adversarial Contamination and Beyond

Stanislav Minsker, Lang Wang

AI总结:

针对高维低秩协方差矩阵估计中存在的对抗污染或重尾分布问题,提出一种自适应低秩结构与污染比例的鲁棒估计器,具备严格偏差保证,并给出高效数值近似算法。

摘要:

我们研究从样本$Y_1,\ldots,Y_n$估计随机向量$Y\in \mathbb R^d$协方差结构的问题。我们关注的场景是:维度$d$相对于样本量$n$较大,但目标协方差矩阵$\Sigma$(精确或近似)具有低秩性。我们假设给定样本满足以下两种情况之一:(a) 受$\varepsilon$-对抗污染,即有$\varepsilon$比例的观测值可能被任意向量替换;(b) 样本独立同分布但底层分布是重尾的,即$Y$的范数仅具有有限四阶矩。我们提出了一种估计器,它既能适配协方差矩阵潜在的低秩结构,也能适配污染数据的比例,并且即使在对底层分布的假设相当弱的情况下,仍具有严格的偏差保证。最后,我们讨论了能够以数值高效的方式近似所提估计器的算法。

英文摘要:

We consider the problem of estimating the covariance structure of a random vector $Y\in \mathbb R^d$ from a sample $Y_1,\ldots,Y_n$. We are interested in the situation when $d$ is large compared to $n$ but the covariance matrix $Σ$ of interest has (exactly or approximately) low rank. We assume that the given sample is (a) $ε$-adversarially corrupted, meaning that $ε$ fraction of the observations could have been replaced by arbitrary vectors, or that (b) the sample is i.i.d. but the underlying distribution is heavy-tailed, meaning that the norm of $Y$ possesses only finite fourth moments. We propose an estimator that is adaptive to the potential low-rank structure of the covariance matrix as well as to the proportion of contaminated data, and admits tight deviation guarantees despite rather weak assumptions on the underlying distribution. Finally, we discuss the algorithms that allow to approximate the proposed estimator in a numerically efficient way.

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。

↑