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 1010.2731math.STcs.ITmath.ITstat.MEstat.TH
收藏

具有可分解正则化子的M-估计高维分析的统一框架

A Unified Framework for High-Dimensional Analysis of M-Estimators with Decomposable Regularizers

Sahand N. Negahban, Pradeep Ravikumar, Martin J. Wainwright, Bin Yu

摘要:

高维统计推断处理的模型中,参数的数量p是可比的或大于样本量n。由于它通常是不可能获得一致的程序,除非$p/n\rightarrow0$,一行最近的工作已经研究了各种类型的低维结构的模型,包括稀疏向量,稀疏和结构化矩阵,低秩矩阵及其组合。在这种情况下,一般的估计方法是解决正则化的最优化问题,它将衡量模型与数据拟合程度的损失函数与鼓励假设结构的正则化函数相结合。本文提供了一个统一的框架,建立一致性和收敛速度的正则化M-估计在高维尺度下。我们国家的一个主要定理,并展示它如何可以用来重新推导出一些现有的结果,也获得了一些新的结果的一致性和收敛速度,在$\ell_2$错误和相关的规范。我们的分析还确定了损失和正则化函数的两个关键属性,称为限制强凸性和可分解性,确保相应的正则化M-估计具有快速的收敛速度,在许多研究充分的情况下是最优的。

英文摘要:

High-dimensional statistical inference deals with models in which the the number of parameters p is comparable to or larger than the sample size n. Since it is usually impossible to obtain consistent procedures unless $p/n\rightarrow0$, a line of recent work has studied models with various types of low-dimensional structure, including sparse vectors, sparse and structured matrices, low-rank matrices and combinations thereof. In such settings, a general approach to estimation is to solve a regularized optimization problem, which combines a loss function measuring how well the model fits the data with some regularization function that encourages the assumed structure. This paper provides a unified framework for establishing consistency and convergence rates for such regularized M-estimators under high-dimensional scaling. We state one main theorem and show how it can be used to re-derive some existing results, and also to obtain a number of new results on consistency and convergence rates, in both $\ell_2$-error and related norms. Our analysis also identifies two key properties of loss and regularization functions, referred to as restricted strong convexity and decomposability, that ensure corresponding regularized M-estimators have fast convergence rates and which are optimal in many well-studied cases.

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。

↑