Optimal Estimation of High-Dimensional Covariance Matrices with Missing and Noisy Data

The estimation of covariance matrices is very important in many fields, such as statistics. In real applications, data are frequently influenced by high dimensions and noise. However, most relevant studies are based on complete data. This paper studies the optimal estimation of high-dimensional covariance matrices based on missing and noisy sample under the norm. First, the model with sub-Gaussian additive noise is presented. The generalized sample covariance is then modified to define a hard thresholding estimator , and the minimax upper bound is derived. After that, the minimax lower bound is derived, and it is concluded that the estimator presented in this article is rate-optimal. Finally, numerical simulation analysis is performed. The result shows that for missing samples with sub-Gaussian noise, if the true covariance matrix is sparse, the hard thresholding estimator outperforms the traditional estimate method.

Two Stage Estimation and Its Covariance Matrix in Multivariate Seemingly Unrelated Regression System

Multivariate 看起来无关的回归系统首先被提起，二个阶段评价和它的协变性矩阵被给。文学的结果[1-5 ] 在这份报纸被扩大。

Underdetermined DOA estimation via multiple time-delay covariance matrices and deep residual network

Higher-order statistics based approaches and signal sparseness based approaches have emerged in recent decades to resolve the underdetermined direction-of-arrival(DOA)estimation problem.These model-based methods face great challenges in practical applications due to high computational complexity and dependence on ideal assumptions.This paper presents an effective DOA estimation approach based on a deep residual network(DRN)for the underdetermined case.We first extract an input feature from a new matrix calculated by stacking several covariance matrices corresponding to different time delays.We then provide the input feature to the trained DRN to construct the super resolution spectrum.The DRN learns the mapping relationship between the input feature and the spatial spectrum by training.The proposed approach is superior to existing model-based estimation methods in terms of calculation efficiency,independence of source sparseness and adaptive capacity to non-ideal conditions(e.g.,low signal to noise ratio,short bit sequence).Simulations demonstrate the validity and strong performance of the proposed algorithm on both overdetermined and underdetermined cases.

IMPROVED ESTIMATES OF THE COVARIANCE MATRIX IN GENERAL LINEAR MIXED MODELS

In this article, the problem of estimating the covariance matrix in general linear mixed models is considered. Two new classes of estimators obtained by shrinking the eigenvalues towards the origin and the arithmetic mean, respectively, are proposed. It is shown that these new estimators dominate the unbiased estimator under the squared error loss function. Finally, some simulation results to compare the performance of the proposed estimators with that of the unbiased estimator are reported. The simulation results indicate that these new shrinkage estimators provide a substantial improvement in risk under most situations.

On convergence of covariance matrix of empirical Bayes hyper-parameter estimator

Regularized system identification has become the research frontier of system identification in the past decade.One related core subject is to study the convergence properties of various hyper-parameter estimators as the sample size goes to infinity.In this paper,we consider one commonly used hyper-parameter estimator,the empirical Bayes(EB).Its convergence in distribution has been studied,and the explicit expression of the covariance matrix of its limiting distribution has been given.However,what we are truly interested in are factors contained in the covariance matrix of the EB hyper-parameter estimator,and then,the convergence of its covariance matrix to that of its limiting distribution is required.In general,the convergence in distribution of a sequence of random variables does not necessarily guarantee the convergence of its covariance matrix.Thus,the derivation of such convergence is a necessary complement to our theoretical analysis about factors that influence the convergence properties of the EB hyper-parameter estimator.In this paper,we consider the regularized finite impulse response(FIR)model estimation with deterministic inputs,and show that the covariance matrix of the EB hyper-parameter estimator converges to that of its limiting distribution.Moreover,we run numerical simulations to demonstrate the efficacy of ourtheoretical results.

Direction of arrival estimation method based on quantum electromagnetic field optimization in the impulse noise

In order to resolve direction finding problems in the impulse noise,a direction of arrival(DOA)estimation method is proposed.The proposed DOA estimation method can restrain the impulse noise by using infinite norm exponential kernel covariance matrix and obtain excellent performance via the maximumlikelihood(ML)algorithm.In order to obtain the global optimal solutions of this method,a quantum electromagnetic field optimization(QEFO)algorithm is designed.In view of the QEFO algorithm,the proposed method can resolve the difficulties of DOA estimation in the impulse noise.Comparing with some traditional DOA estimation methods,the proposed DOA estimation method shows high superiority and robustness for determining the DOA of independent and coherent sources,which has been verified via the Monte-Carlo experiments of different schemes,especially in the case of snapshot deficiency,low generalized signal to noise ratio(GSNR)and strong impulse noise.Beyond that,the Cramer-Rao bound(CRB)of angle estimation in the impulse noise and the proof of the convergence of the QEFO algorithm are provided in this paper.

Texture invariant estimation of equivalent number of looks based on log-cumulants in polarimetric radar imagery

A novel estimation of the equivalent number of looks (ENL) is proposed in statistical modeling of multilook polarimetric synthetic aperture radar (PolSAR) images for the product model, which is based on the log-determinant moments (LDM). The LDM estimators discovered by looking at certain log-cumulants of the intensities of different polarization channels and the multilook polarimetric covariance matrix, which can be used for both the Gaussian model and all product models. This estimator has analytic expressions, and uses the full covariance matrix and intensities as input, which makes more statistical information available. Experiments based on simulated data and real data are performed. The comparisons among the widely used methods of equivalent number of looks (ENL) estimation for the product model such as K and G0 distributions show that the performance of the LDM estimator is outstanding. The performance of estimators for the real data of San Francisco and Flevoland is analyzed and the results are according to those of simulated data. Finally, it can be concluded that the LDM estimator is well robust to each product model with low computational complexity and high accuracy. © 1990-2011 Beijing Institute of Aerospace Information.

Sparse Estimation of High-Dimensional Inverse Covariance Matrices with Explicit Eigenvalue Constraints

Firstly,this paper proposes a generalized log-determinant optimization model with the purpose of estimating the high-dimensional sparse inverse covariance matrices.Under the normality assumption,the zero components in the inverse covariance matrices represent the conditional independence between pairs of variables given all the other variables.The generalized model considered in this study,because of the setting of the eigenvalue bounded constraints,covers a large number of existing estimators as special cases.Secondly,rather than directly tracking the challenging optimization problem,this paper uses a couple of alternating direction methods of multipliers(ADMM)to solve its dual model where 5 separable structures are contained.The first implemented algorithm is based on a single Gauss–Seidel iteration,but it does not necessarily converge theoretically.In contrast,the second algorithm employs the symmetric Gauss–Seidel(sGS)based ADMM which is equivalent to the 2-block iterative scheme from the latest sGS decomposition theorem.Finally,we do numerical simulations using the synthetic data and the real data set which show that both algorithms are very effective in estimating high-dimensional sparse inverse covariance matrix.

分布式散射体相位估计奇异值分解法

常规的分布式散射体(DS)相位估计方法需要生成全组合干涉对以构建样本协方差矩阵(SCM),然后根据SCM的统计特性估计DS相位,这一过程不但计算耗时,而且占据大量存储空间。本文提出了一种基于奇异值分解技术的DS相位快速估计方法(SVDI)。该方法分析的对象是单主影像干涉对组成的干涉相位矩阵而非全组合干涉对组成的SCM,因而可以有效提高计算效率、节省存储空间。并且,理论上证明了在一定条件下SVDI的结果与常规的特征值分解方法(EVD)是一致的。模拟数据和真实SAR数据的结果表明,SVDI算法有更高的计算效率,并且其相位估计精度以及形变解算精度与常规算法是一致的。

基于小快拍场景的联合校正稳健波束形成算法

针对传统的自适应波束形成算法在目标导向矢量失配及接收数据的协方差矩阵存在误差时,性能急剧下降的问题,提出了一种基于小快拍场景的联合协方差矩阵重构,及导向矢量优化的稳健波束形成算法。对不确定集约束求解得到干扰导向矢量,根据稀疏干扰来向的导向矢量近似正交,求出干扰导向矢量对应的干扰功率,从而完成协方差矩阵重构;对期望信号来向及其邻域进行权值求解,对加权后的数据特征分解,利用多信号分类(Multiple Signal Classification, MUSIC)谱估计算法对信号区域积分得到信号协方差矩阵,将其主特征值近似为期望信号的导向矢量完成重新估计。仿真结果表明,在无误差时,算法输出信干噪比(Signal to Interference Plus Noise Ratio, SINR)接近理论最优;在多种误差环境下输出性能随信噪比(Signal to Noise Ratio, SNR)的变化均具有较好的稳健性,并且在信号来向可精准形成波束;在小快拍时可以较快收敛至理论最优值。

Sparse and Low-Rank Covariance Matrix Estimation

This paper aims at achieving a simultaneously sparse and low-rank estimator from the semidefinite population covariance matrices.We first benefit from a convex optimization which develops l1-norm penalty to encourage the sparsity and nuclear norm to favor the low-rank property.For the proposed estimator,we then prove that with high probability,the Frobenius norm of the estimation rate can be of order O(√((slgg p)/n))under a mild case,where s and p denote the number of nonzero entries and the dimension of the population covariance,respectively and n notes the sample capacity.Finally,an efficient alternating direction method of multipliers with global convergence is proposed to tackle this problem,and merits of the approach are also illustrated by practicing numerical simulations.

High dimensional covariance matrix estimation using multi-factor models from incomplete information

Covariance matrix plays an important role in risk management, asset pricing, and portfolio allocation. Covariance matrix estimation becomes challenging when the dimensionality is comparable or much larger than the sample size. A widely used approach for reducing dimensionality is based on multi-factor models. Although it has been well studied and quite successful in many applications, the quality of the estimated covariance matrix is often degraded due to a nontrivial amount of missing data in the factor matrix for both technical and cost reasons. Since the factor matrix is only approximately low rank or even has full rank, existing matrix completion algorithms are not applicable. We consider a new matrix completion paradigm using the factor models directly and apply the alternating direction method of multipliers for the recovery. Numerical experiments show that the nuclear-norm matrix completion approaches are not suitable but our proposed models and algorithms are promising.

Sphericity and Identity Test for High-dimensional Covariance Matrix Using Random Matrix Theory

This paper addresses the issue of testing sphericity and identity of high-dimensional population covariance matrix when the data dimension exceeds the sample size.The central limit theorem of the first four moments of eigenvalues of sample covariance matrix is derived using random matrix theory for generally distributed populations.Further,some desirable asymptotic properties of the proposed test statistics are provided under the null hypothesis as data dimension and sample size both tend to infinity.Simulations show that the proposed tests have a greater power than existing methods for the spiked covariance model.

Efficient Distributed Estimation of High-dimensional Sparse Precision Matrix for Transelliptical Graphical Models

In this paper,distributed estimation of high-dimensional sparse precision matrix is proposed based on the debiased D-trace loss penalized lasso and the hard threshold method when samples are distributed into different machines for transelliptical graphical models.At a certain level of sparseness,this method not only achieves the correct selection of non-zero elements of sparse precision matrix,but the error rate can be comparable to the estimator in a non-distributed setting.The numerical results further prove that the proposed distributed method is more effective than the usual average method.

无误差阵列协方差矩阵分离的阵列自校正方法

针对高分辨方位估计方法受阵列幅度相位影响导致性能退化的问题,提出一种无误差阵列协方差矩阵分离的阵列自校正方法。该方法利用协方差矩阵重构方法获取近似无误差阵列的协方差矩阵,以弱化协方差矩阵中的阵列误差,并利用特征结构配置方法求解幅度和相位误差。迭代上述重构方法和特征结构配置方法,实现从未校正阵列的协方差矩阵中分离出无误差阵列的协方差矩阵和幅度相位误差矩阵。仿真结果表明,该方法准确地估计阵列误差,利用重构协方差矩阵进行方位估计能够提高方位估计精度和分辨力。湖试试验结果表明,经阵列校正后,空间中方位角度邻近的声源和干扰目标可被分辨。

一种基于组合子阵协方差矩阵的阵列扩展方法

针对阵列在低信噪比条件下信号检测概率低且方位估计性能下降的问题,提出一种基于组合子阵协方差矩阵的线列阵扩展方法。该方法将阵列划分为奇偶子阵,根据子阵的互协方差与自协方差矩阵构建扩展接收数据,对扩展接收数据进行组合作为最终的阵列接收数据进行处理,由此在突破阵列物理孔径的基础上避免仅使用奇偶阵元互协方差重构接收数据时产生的栅瓣问题。仿真结果表明:新方法可以降低波束输出的旁瓣,具有较好的弱目标检测能力和方位分辨力;相比于基于奇偶阵元互协方差的阵列扩展方法,新方法可有效提升方位估计精度,且不存在栅瓣问题。

基于稀疏线阵协方差矩阵重构的DOA估计方法研究

相比均匀线阵(Uniform Linear Array,ULA),相同阵元数目下稀疏线阵(Sparse Linear Array,SLA)的抗耦合效应更好,阵列孔径更大,到达方向(Direction of Arrival,DOA)估计的自由度(Degrees Of Freedom,DOF)更高,因而近年来得到了广泛的研究。为了可以进行高DOF的DOA估计,学者们开始研究SLA的差分虚拟阵元,差分虚拟阵元对应的协方差矩阵相比原阵元对应的协方差矩阵维度更大,因而估计的DOF更高。当SLA的差分虚拟阵元连续取值时,可以利用已有阵元的接收信息,得到SLA的协方差矩阵,在该矩阵的基础之上构建差分虚拟阵元的协方差矩阵进而进行DOA估计。然而,当SLA的差分虚拟阵元存在孔洞时,即差分虚拟阵元不能连续取值时,不能直接利用重构的协方差矩阵进行DOA估计,需要恢复完全增广协方差矩阵的信息再进行DOA估计。对于该问题,本文基于矢量化后原协方差矩阵和虚拟差分阵协方差矩阵的误差分布情况,并结合完全增广协方差矩阵的低秩特性和半正定特性来构建优化问题。通过求解该问题来恢复维度更高的完全增广协方差矩阵。最后对该矩阵进行奇异值分解,利用多重信号分类(Multiple Signal Classification,MUSIC)算法就可以获得多源的空间谱。本文最后通过数值仿真试验验证了所提算法可以实现高DOF的DOA估计,并且相比于现有算法,本文所提算法对欠定DOA估计的效果更好,多源DOA估计的精度更高,产生的误差更小。

基于声压振速联合处理的稀疏协方差DOA估计

为充分利用矢量水听器中声压振速信息之间的关系来提高DOA估计精度,本文提出了基于声压振速联合处理的稀疏协方差DOA(Direction ofArrival)估计方法。该方法首先利用声压振速之间的相关性,构造阵列协方差矩阵;其次,将空间入射角度集合进行等角度划分,构造超完备冗余字典;然后,在过完备基上寻找阵列协方差矩阵的最稀疏系数,利用系数向量中的非零行所对应的行号得到DOA估计值。将该算法与CBF算法及L1-SVD算法进行对比仿真实验,结果表明,在信号源数分别为3,4,5的情形下,本文所提算法在低信噪比和小快拍数情形时,具有更低的均方根误差,DOA估计性能优势明显。

基于互质阵列的协方差矩阵重构算法

针对基于互质阵列波达方向(direction of arrival, DOA)估计方法对连续虚拟阵元得到的样本协方差矩阵信息利用率不高的问题,提出一种基于互质阵列的协方差矩阵重构算法。该算法利用最大连续虚拟均匀线阵协方差矩阵的每一行元素进行Toeplitz矩阵重构,再对这些矩阵加权求和获得新的满秩协方差矩阵,提高对接收数据的利用率并消除噪声贡献对DOA估计结果的影响。理论分析和仿真结果表明,该算法能实现欠定DOA估计,在低信噪比、小快拍数、入射角度间隔小条件下有良好的角度估计精度。

A New Estimator of Covariance Matrix via Partial Iwasawa Coordinates

This paper is concerned with the problem of improving the estimator of covariance matrix under Stein's loss. By the partial Iwasawa coordinates of covariance matrix, the corresponding risk can be split into three parts. One can use the information in the weighted matrix of weighted quadratic loss to improve one part of risk. However, this paper indirectly takes advantage of the information in the sample mean and reuses Iwasawa coordinates to improve the rest of risk. It is worth mentioning that the process above can be repeated. Finally, a Monte Carlo simulation study is carried out to verify the theoretical results.