arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.13312cs.DScs.LGmath.STstat.MLstat.TH
收藏

近似矩阵乘时的抗差高斯协方差估计

Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time

Microsoft Research AI(微软研究院人工智能部门);University of Washington(华盛顿大学)

Jerry Li, Guanghao Ye

摘要:

稳健的协方差估计是以下在高维统计中被充分研究的问题:给定来自$d$维高斯$\mathcal{N}(\boldsymbol{0}, Σ)$的$N$样本,但是其中样本的$\varepsilon$分数被任意损坏,输出$\widehatΣ$最小化$\mathcal{N}(\boldsymbol{0}, Σ)$和$\mathcal{N}(\boldsymbol{0}, \widehatΣ)$之间的总变化距离。这对应于学习Frobenius范数的自然仿射不变变体中的$Σ$,称为\emph{Mahalanobis norm}。Cheng等人先前的工作证明了一种算法,该算法在给定$N = Ω(d^2 / \varepsilon^2)$样本的情况下实现了$O(\varepsilon \log 1 / \varepsilon)$的接近最优的误差,而且,他们的算法在时间$\widetilde{O}(T(N, d) \log κ/ \mathrm{poly} (\varepsilon))$中运行,其中$T(N, d)$是将$d \times N$矩阵乘以其转置所花费的时间,$κ$是$Σ$的条件数。当$\varepsilon$相对较小时,它们在运行时对$1/\varepsilon$的多项式依赖性非常大。在本文中,我们展示了一种新的算法,实现了相同的统计保证,但运行时间$\widetilde{O} (T(N, d) \log κ)$。特别是,我们的运行时不依赖于$\varepsilon$。当$Σ$是合理的条件,我们的运行时间匹配的最快的算法的协方差估计没有离群值,多对数因子,表明我们可以得到鲁棒性基本上是“免费的。"

英文摘要:

Robust covariance estimation is the following, well-studied problem in high dimensional statistics: given $N$ samples from a $d$-dimensional Gaussian $\mathcal{N}(\boldsymbol{0}, Σ)$, but where an $\varepsilon$-fraction of the samples have been arbitrarily corrupted, output $\widehatΣ$ minimizing the total variation distance between $\mathcal{N}(\boldsymbol{0}, Σ)$ and $\mathcal{N}(\boldsymbol{0}, \widehatΣ)$. This corresponds to learning $Σ$ in a natural affine-invariant variant of the Frobenius norm known as the \emph{Mahalanobis norm}. Previous work of Cheng et al demonstrated an algorithm that, given $N = Ω(d^2 / \varepsilon^2)$ samples, achieved a near-optimal error of $O(\varepsilon \log 1 / \varepsilon)$, and moreover, their algorithm ran in time $\widetilde{O}(T(N, d) \log κ/ \mathrm{poly} (\varepsilon))$, where $T(N, d)$ is the time it takes to multiply a $d \times N$ matrix by its transpose, and $κ$ is the condition number of $Σ$. When $\varepsilon$ is relatively small, their polynomial dependence on $1/\varepsilon$ in the runtime is prohibitively large. In this paper, we demonstrate a novel algorithm that achieves the same statistical guarantees, but which runs in time $\widetilde{O} (T(N, d) \log κ)$. In particular, our runtime has no dependence on $\varepsilon$. When $Σ$ is reasonably conditioned, our runtime matches that of the fastest algorithm for covariance estimation without outliers, up to poly-logarithmic factors, showing that we can get robustness essentially "for free."

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。

↑