We analyze the performance of the Tukey median estimator under total variation (TV) distance corruptions. Previous results show that under Huber's additive corruption model, the breakdown point is 1/3 for high-dimensional halfspace-symmetric distributions. We show that under TV corruptions, the breakdown point reduces to 1/4 for the same set of distributions. We also show that a certain projection algorithm can attain the optimal breakdown point of 1/2. Both the Tukey median estimator and the projection algorithm achieve sample complexity linear in dimension.
The limit of finite sample breakdown point of Tukey's halfspace median for general data
在数据集和底层分布的特定条件下,文献中给出了Tukey半空间中值($\frac{1} {3}$)有限样本崩溃点的极限.在本文中,我们建立了\emph{weaker assumption}下的基础分布(半空间对称性)和数据集(不需要在一般位置)的结果。作为我们推导的副产品,还获得了数据集\emph{not necessary in general position}的Tukey的样本深度区域的表示。
Generalization Bounds in the Presence of Outliers: a Median-of-Means Study
Università degli Studi di Milano(米兰大学);Télécom Paris, Institut Polytechnique de Paris(巴黎综合理工学院电信学院)
与经验平均值相反,均值中位数(MoM)是平方可积r. v. $Z$的平均值$θ$的估计量,即使$Z$不表现出亚高斯尾部行为,也可以围绕其建立精确的非渐近置信界限。由于它在重尾数据上实现了高置信度,MoM在机器学习中找到了各种应用,用于设计对非典型观测不敏感的训练程序。最近,一项新的工作正在试图描述和利用MoM处理损坏数据的能力。在这种情况下,目前的工作提出了一个一般性的研究MoM的浓度属性下的污染制度,提供了一个清晰的理解的影响的离群值的比例和选择的块的数量。该分析扩展到(多样本)$U$ -统计,即观察元组的平均值,由于诱导的依赖性而引起额外的挑战。最后,我们表明后面的界限可以以简单的方式用于推导污染环境中成对学习的泛化保证,并提出了一种计算可证明可靠的决策函数的算法。
Bias robustness of depth estimators in multivariate settings
FAMAF, National University of Córdoba(科尔多瓦国立大学 FAMAF);CIEM and CONICET, Argentina(阿根廷 CIEM 和 CONICET);Department of Mathematics, National University of Río Cuarto, Argentina(里奥夸尔托国立大学数学系)
Convex Clustering Redefined: Robust Learning with the Median of Means Estimator
Indian Statistical Institute, Kolkata(印度统计研究院,科希马);Department of Statistics and Data Science, University of Texas at Austin(德克萨斯大学奥斯汀分校统计与数据科学系);Electronics and Communication Sciences, Indian Statistical Institute, Kolkata(印度统计研究院,科希马电子与通信科学);Department of Statistics, University of Oxford(牛津大学统计系);Department of Statistics, University of Michigan(密歇根大学统计系)