arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.06292stat.MLcs.LGmath.STstat.TH
收藏

低秩矩阵值函数的非参数估计

Nonparametric Estimation of Low Rank Matrix Valued Function

Georgia Institute of Technology(佐治亚理工学院)

Fan Zhou

摘要:

设$A:[0,1]\rightarrow\mathbb{H}_m$(Hermitian矩阵空间)是一个低秩的矩阵值函数,其元素在Hölder类$Σ(β,L)$中.本文的目的是研究基于回归模型$\mathbb{E}(Y_j|τ_j,X_j) = \langle A(τ_j), X_j \rangle,$的$A$的统计估计,其中$τ_j$是i.i.d.均匀分布在$[0,1]$中,$X_j$为i.i.d.。矩阵完备采样矩阵$Y_j$是独立有界响应。我们提出了一个创新的核范数惩罚局部多项式估计,并建立了一个上界的点的风险Frobenius范数测量。然后,我们推广这个估计的整体和证明了一个上界的综合风险衡量的$L_2$ -范数。我们还提出了另一种新的估计偏差减少内核的基础上研究的情况下,$A$不一定是低秩和建立一个上限的风险衡量的$L_{\infty}$ -范数。我们表明,所获得的利率都是最佳的一些对数因子在极大极小意义下。最后,我们提出了一个自适应估计过程的基础上Lepskii的方法和模型选择与数据分裂,这是计算效率高,易于实现和并行化。

英文摘要:

Let $A:[0,1]\rightarrow\mathbb{H}_m$ (the space of Hermitian matrices) be a matrix valued function which is low rank with entries in Hölder class $Σ(β,L)$. The goal of this paper is to study statistical estimation of $A$ based on the regression model $\mathbb{E}(Y_j|τ_j,X_j) = \langle A(τ_j), X_j \rangle,$ where $τ_j$ are i.i.d. uniformly distributed in $[0,1]$, $X_j$ are i.i.d. matrix completion sampling matrices, $Y_j$ are independent bounded responses. We propose an innovative nuclear norm penalized local polynomial estimator and establish an upper bound on its point-wise risk measured by Frobenius norm. Then we extend this estimator globally and prove an upper bound on its integrated risk measured by $L_2$-norm. We also propose another new estimator based on bias-reducing kernels to study the case when $A$ is not necessarily low rank and establish an upper bound on its risk measured by $L_{\infty}$-norm. We show that the obtained rates are all optimal up to some logarithmic factor in minimax sense. Finally, we propose an adaptive estimation procedure based on Lepskii's method and model selection with data splitting which is computationally efficient and can be easily implemented and parallelized.

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。

↑