arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0909.0861math.STstat.TH
收藏

Dantzig选择器与稀疏预言不等式

The Dantzig selector and sparsity oracle inequalities

Vladimir Koltchinskii

摘要:

设\[Y_j=f_*(X_j)+ξ_j,\qquad j=1,...,n,\],其中$X,X_1,...,X_n$为i.i.d.。可测空间$(S,\mathcal{A})$中的随机变量的分布为$Π$和$ξ,ξ_1,... ,ξ_n$,它们是独立同分布的。随机变量与${\mathbb{E}}ξ=0$独立于$(X_1,...,X_n).$给定字典$h_1,...,h_N:S\mapsto{\mathbb{R}},$让$f_λ:=\sum_{j=1}^Nλ_jh_j$,$λ=(λ_1,...,λ_N)\in{\mathbb{R}}^N.$给定$\varepsilon>0,$定义\[\hatΛ_{\varepsilon}:=\Biggl\{\lam bda\in{\mathbb{R}}^N:\max_{1\leq k\leq N}\Biggl|n^{-1}\sum_{j=1}^n\big l(f_λ(X_j)-Y_j\bigr)h_k(X_j)\Biggr|\leq\varepsilon \Biggr\}\]和\[\hatλ:=\hatλ^{\varepsilon}\in \operatorname {Arg min}\limits_{λ\in\hatΛ_{\varepsilon}}\|λ\|_{\ell_1}.\]在$f_*:=f_{λ^*},λ^*\in {\mathbb{R}}^N,$ Candes和Tao [Ann. Statist. 35(2007)2313--2351]建议使用$\hatλ$作为$λ^*.$的估计器,他们称这个估计器为“Dantzig选择器”。我们研究了随机设计回归模型的$f_{\hatλ}$作为$f_*$的估计量的性质,扩展了Candes和Tao的一些结果(并提供了这些结果的替代证明)。

英文摘要:

Let \[Y_j=f_*(X_j)+ξ_j,\qquad j=1,...,n,\] where $X,X_1,...,X_n$ are i.i.d. random variables in a measurable space $(S,\mathcal{A})$ with distribution $Π$ and $ξ,ξ_1,... ,ξ_n$ are i.i.d. random variables with ${\mathbb{E}}ξ=0$ independent of $(X_1,...,X_n).$ Given a dictionary $h_1,...,h_N:S\mapsto{\mathbb{R}},$ let $f_λ:=\sum_{j=1}^Nλ_jh_j$, $λ=(λ_1,...,λ_N)\in{\mathbb{R}}^N.$ Given $\varepsilon>0,$ define \[\hatΛ_{\varepsilon}:=\Biggl\{\lam bda\in{\mathbb{R}}^N:\max_{1\leq k\leq N}\Biggl|n^{-1}\sum_{j=1}^n\big l(f_λ(X_j)-Y_j\bigr)h_k(X_j)\Biggr|\leq\varepsilon \Biggr\}\] and \[\hatλ:=\hatλ^{\varepsilon}\in \operatorname {Arg min}\limits_{λ\in\hatΛ_{\varepsilon}}\|λ\|_{\ell_1}.\] In the case where $f_*:=f_{λ^*},λ^*\in {\mathbb{R}}^N,$ Candes and Tao [Ann. Statist. 35 (2007) 2313--2351] suggested using $\hatλ$ as an estimator of $λ^*.$ They called this estimator ``the Dantzig selector''. We study the properties of $f_{\hatλ}$ as an estimator of $f_*$ for regression models with random design, extending some of the results of Candes and Tao (and providing alternative proofs of these results).

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。

↑