arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.08137stat.MLcs.DScs.LG
收藏

近似线性时间下的最优稳健线性回归

Optimal Robust Linear Regression in Nearly Linear Time

University of California Berkeley(加州大学伯克利分校);EPFL(洛桑联邦理工学院)

Yeshwanth Cherapanamjeri, Efe Aras, Nilesh Tripuraneni, Michael I. Jordan, Nicolas Flammarion, Peter L. Bartlett

摘要:

我们研究了高维鲁棒线性回归的问题,其中学习者可以从生成模型$Y = \langle X,w^* \rangle + ε$($X \in \mathbb{R}^d$和$ε$独立)访问$n$样本,其中样本的$η$部分已被反向损坏。我们提出了这个问题的估计在两个设置:(i)$X$是L4-L2 hypercontractive,$\mathbb{E} [XX^\top]$有界的条件数和$ε$有界的方差和(ii)$X$是次高斯单位二阶矩和$ε$是次高斯。在这两种设置中,我们的估计:(a)实现最佳的样本复杂性和恢复保证高达对数因子和(b)运行在近线性时间($\tilde{O}(nd / η^6)$)。在我们的工作之前,多项式时间算法实现接近最佳的样本复杂性只知道在设置$X$是高斯与身份协方差和$ε$是高斯,并没有线性时间估计已知的鲁棒线性回归在任何设置。我们的估计器及其分析利用了最近在构建更快的算法以进行稳健的均值估计以改善运行时间方面的发展,并改进了测量参数的浓度以及高斯舍入技术以改善统计样本的复杂性。

英文摘要:

We study the problem of high-dimensional robust linear regression where a learner is given access to $n$ samples from the generative model $Y = \langle X,w^* \rangle + ε$ (with $X \in \mathbb{R}^d$ and $ε$ independent), in which an $η$ fraction of the samples have been adversarially corrupted. We propose estimators for this problem under two settings: (i) $X$ is L4-L2 hypercontractive, $\mathbb{E} [XX^\top]$ has bounded condition number and $ε$ has bounded variance and (ii) $X$ is sub-Gaussian with identity second moment and $ε$ is sub-Gaussian. In both settings, our estimators: (a) Achieve optimal sample complexities and recovery guarantees up to log factors and (b) Run in near linear time ($\tilde{O}(nd / η^6)$). Prior to our work, polynomial time algorithms achieving near optimal sample complexities were only known in the setting where $X$ is Gaussian with identity covariance and $ε$ is Gaussian, and no linear time estimators were known for robust linear regression in any setting. Our estimators and their analysis leverage recent developments in the construction of faster algorithms for robust mean estimation to improve runtimes, and refined concentration of measure arguments alongside Gaussian rounding techniques to improve statistical sample complexities.

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。

↑