arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.08020math.STstat.TH
收藏

受损高斯设计的限制性eigenvalue性质

Restricted eigenvalue property for corrupted Gaussian designs

Philip Thompson, Arnak S. Dalalyan

摘要:

基于凸松弛方法构造易于处理的鲁棒估计,我们给出了保证高斯设计的限制特征值型条件的增广概念的样本量条件.当样本被响应变量或设计矩阵中的离群值破坏时,这种概念适用于高斯线性模型和多变量高斯模型中的高维鲁棒推断。我们的证明技术依赖于两个随机的双线性型非常不同的行为,同时下限和上界。这种同时边界用于平衡参数向量和估计的损坏向量之间的相互作用,以及用于控制设计中损坏的存在。我们的技术的优点是不依赖于相关的高斯系综的极端奇异值的已知界限,也不使用相互不相干参数。我们的分析的一个相关的后果,相比以前的工作,是一个显着尖锐的限制本征值常数可以在较弱的假设下获得。特别地,允许未知参数的稀疏性和异常值的数量彼此完全独立。

英文摘要:

Motivated by the construction of tractable robust estimators via convex relaxations, we present conditions on the sample size which guarantee an augmented notion of Restricted Eigenvalue-type condition for Gaussian designs. Such a notion is suitable for high-dimensional robust inference in a Gaussian linear model and a multivariate Gaussian model when samples are corrupted by outliers either in the response variable or in the design matrix. Our proof technique relies on simultaneous lower and upper bounds of two random bilinear forms with very different behaviors. Such simultaneous bounds are used for balancing the interaction between the parameter vector and the estimated corruption vector as well as for controlling the presence of corruption in the design. Our technique has the advantage of not relying on known bounds of the extreme singular values of the associated Gaussian ensemble nor on the use of mutual incoherence arguments. A relevant consequence of our analysis, compared to prior work, is that a significantly sharper restricted eigenvalue constant can be obtained under weaker assumptions. In particular, the sparsity of the unknown parameter and the number of outliers are allowed to be completely independent of each other.

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。

↑