arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15618math.STcs.DScs.LGstat.MLstat.TH
收藏

基于稳定性的次高斯率下粗差稳健均值估计

Outlier Robust Mean Estimation with Subgaussian Rates via Stability

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);University of California, San Diego(加利福尼亚大学圣迭戈分校)

Ilias Diakonikolas, Daniel M. Kane, Ankit Pensia

摘要:

本文研究了有限协方差假设下高维均值的离群稳健估计问题,并在更广泛的意义上研究了有限低阶矩假设下的高维均值估计问题。我们考虑了一个标准的稳定性条件,从最近的鲁棒统计文献,并证明,除了指数小的故障概率,存在一个大部分的内点满足这个条件。作为一个推论,它遵循的是一些最近开发的鲁棒均值估计算法,包括迭代滤波和非凸梯度下降,给出最佳误差估计(近)亚高斯率。以前的分析,这些算法给出了显着次优率。作为推论,我们的方法,我们得到了第一个计算效率的算法与次高斯率的离群稳健的均值估计在强污染模型下的有限协方差假设。

英文摘要:

We study the problem of outlier robust high-dimensional mean estimation under a finite covariance assumption, and more broadly under finite low-degree moment assumptions. We consider a standard stability condition from the recent robust statistics literature and prove that, except with exponentially small failure probability, there exists a large fraction of the inliers satisfying this condition. As a corollary, it follows that a number of recently developed algorithms for robust mean estimation, including iterative filtering and non-convex gradient descent, give optimal error estimators with (near-)subgaussian rates. Previous analyses of these algorithms gave significantly suboptimal rates. As a corollary of our approach, we obtain the first computationally efficient algorithm with subgaussian rate for outlier-robust mean estimation in the strong contamination model under a finite covariance assumption.

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。

↑