arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.03058math.STmath.OCstat.TH
收藏

近似线性时间下均值向量的抗差次高斯估计

Robust subgaussian estimation of a mean vector in nearly linear time

Jules Depersin, Guillaume Lecué

摘要:

我们构建了一个算法,运行时间$\tilde{\mathcal O}(N d + uK d)$,这是强大的离群值和重尾数据,并实现了亚高斯率从[Lugosi,Mendelson] \begin{equation}\label{eq:intro_subgaus_rate} \sqrt{\frac{{\rm Tr}(Σ)}{N}}+\sqrt{\frac{||Σ||_{op}K}{N}} \end{equation}概率至少为$1-\exp(-c_0K)-\exp(-c_1 u)$其中$Σ$是信息数据的协方差阵,$K\in\{1, \ldots, K\}$是一些参数(块平均数)和$u>0$是该算法的另一个参数。当$K\geq c_1 |\mathcal O|$(其中$|\mathcal O|$是数据库中离群值的数量)且仅假设信息数据具有二阶矩时,可实现该比率。该算法完全依赖于数据,在其构造中不使用离群值的比例,也不使用上述比率。它的构建结合了最近开发的中位数估计和覆盖半定规划工具[Chen,Diakonikolas,Ge]和[Peng,Tangwongsan,Zhang]。

英文摘要:

We construct an algorithm, running in time $\tilde{\mathcal O}(N d + uK d)$, which is robust to outliers and heavy-tailed data and which achieves the subgaussian rate from [Lugosi, Mendelson] \begin{equation}\label{eq:intro_subgaus_rate} \sqrt{\frac{{\rm Tr}(Σ)}{N}}+\sqrt{\frac{||Σ||_{op}K}{N}} \end{equation}with probability at least $1-\exp(-c_0K)-\exp(-c_1 u)$ where $Σ$ is the covariance matrix of the informative data, $K\in\{1, \ldots, K\}$ is some parameter (number of block means) and $u>0$ is another parameter of the algorithm. This rate is achieved when $K\geq c_1 |\mathcal O|$ where $|\mathcal O|$ is the number of outliers in the database and under the only assumption that the informative data have a second moment. The algorithm is fully data-dependent and does not use in its construction the proportion of outliers nor the rate above. Its construction combines recently developed tools for Median-of-Means estimators and covering-Semi-definite Programming [Chen, Diakonikolas, Ge] and [Peng, Tangwongsan, Zhang].

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。

↑