Matrix completion is the extension of compressed sensing.In compressed sensing,we solve the underdetermined equations using sparsity prior of the unknown signals.However,in matrix completion,we solve the underdetermin...Matrix completion is the extension of compressed sensing.In compressed sensing,we solve the underdetermined equations using sparsity prior of the unknown signals.However,in matrix completion,we solve the underdetermined equations based on sparsity prior in singular values set of the unknown matrix,which also calls low-rank prior of the unknown matrix.This paper firstly introduces basic concept of matrix completion,analyses the matrix suitably used in matrix completion,and shows that such matrix should satisfy two conditions:low rank and incoherence property.Then the paper provides three reconstruction algorithms commonly used in matrix completion:singular value thresholding algorithm,singular value projection,and atomic decomposition for minimum rank approximation,puts forward their shortcoming to know the rank of original matrix.The Projected Gradient Descent based on Soft Thresholding(STPGD),proposed in this paper predicts the rank of unknown matrix using soft thresholding,and iteratives based on projected gradient descent,thus it could estimate the rank of unknown matrix exactly with low computational complexity,this is verified by numerical experiments.We also analyze the convergence and computational complexity of the STPGD algorithm,point out this algorithm is guaranteed to converge,and analyse the number of iterations needed to reach reconstruction error.Compared the computational complexity of the STPGD algorithm to other algorithms,we draw the conclusion that the STPGD algorithm not only reduces the computational complexity,but also improves the precision of the reconstruction solution.展开更多
在时分双工(TDD)毫米波大规模多输入多输出(MIMO)系统中,因为波束空间信道具有稀疏性,导致将低维测量数据重建为原始高维信道时会带来较高的复杂度。针对上行链路,在不考虑稀疏度的情况下,将传统优化算法和基于数据驱动的深度学习方法...在时分双工(TDD)毫米波大规模多输入多输出(MIMO)系统中,因为波束空间信道具有稀疏性,导致将低维测量数据重建为原始高维信道时会带来较高的复杂度。针对上行链路,在不考虑稀疏度的情况下,将传统优化算法和基于数据驱动的深度学习方法相结合,提出一种改进的基于深度学习的波束空间信道估计算法。从重建过程入手,通过交替建立梯度下降模块(GDM)和近端映射模块(PMM)来构建网络。首先根据SalehValenzuela信道模型进行理论公式推导并生成信道数据;其次构建一个由传统迭代收缩阈值算法(ISTA)的更新步骤所展开的多层网络,并将数据传输到该网络,每层对应于一次类似ISTA的迭代;最后对训练好的模型进行在线测试,恢复出待估计的信道。构建Py Torch环境,将该算法与正交匹配追踪(OMP)算法、近似消息传递(AMP)算法、可学习的近似消息传递(LAMP)算法、高斯混合LAMP(GM-LAMP)算法进行对比,结果表明:在估计精度方面,所提算法相对表现较好的深度学习算法LAMP、GM-LAMP分别提升约3.07和2.61 d B,较传统算法OMP、AMP分别提升约11.12和9.57 d B;在参数量方面,所提算法较LAMP、GM-LAMP分别减少约39%和69%。展开更多
基金Supported by the National Natural Science Foundation ofChina(No.61271240)Jiangsu Province Natural Science Fund Project(No.BK2010077)Subject of Twelfth Five Years Plans in Jiangsu Second Normal University(No.417103)
摘要Matrix completion is the extension of compressed sensing.In compressed sensing,we solve the underdetermined equations using sparsity prior of the unknown signals.However,in matrix completion,we solve the underdetermined equations based on sparsity prior in singular values set of the unknown matrix,which also calls low-rank prior of the unknown matrix.This paper firstly introduces basic concept of matrix completion,analyses the matrix suitably used in matrix completion,and shows that such matrix should satisfy two conditions:low rank and incoherence property.Then the paper provides three reconstruction algorithms commonly used in matrix completion:singular value thresholding algorithm,singular value projection,and atomic decomposition for minimum rank approximation,puts forward their shortcoming to know the rank of original matrix.The Projected Gradient Descent based on Soft Thresholding(STPGD),proposed in this paper predicts the rank of unknown matrix using soft thresholding,and iteratives based on projected gradient descent,thus it could estimate the rank of unknown matrix exactly with low computational complexity,this is verified by numerical experiments.We also analyze the convergence and computational complexity of the STPGD algorithm,point out this algorithm is guaranteed to converge,and analyse the number of iterations needed to reach reconstruction error.Compared the computational complexity of the STPGD algorithm to other algorithms,we draw the conclusion that the STPGD algorithm not only reduces the computational complexity,but also improves the precision of the reconstruction solution.
摘要在时分双工(TDD)毫米波大规模多输入多输出(MIMO)系统中,因为波束空间信道具有稀疏性,导致将低维测量数据重建为原始高维信道时会带来较高的复杂度。针对上行链路,在不考虑稀疏度的情况下,将传统优化算法和基于数据驱动的深度学习方法相结合,提出一种改进的基于深度学习的波束空间信道估计算法。从重建过程入手,通过交替建立梯度下降模块(GDM)和近端映射模块(PMM)来构建网络。首先根据SalehValenzuela信道模型进行理论公式推导并生成信道数据;其次构建一个由传统迭代收缩阈值算法(ISTA)的更新步骤所展开的多层网络,并将数据传输到该网络,每层对应于一次类似ISTA的迭代;最后对训练好的模型进行在线测试,恢复出待估计的信道。构建Py Torch环境,将该算法与正交匹配追踪(OMP)算法、近似消息传递(AMP)算法、可学习的近似消息传递(LAMP)算法、高斯混合LAMP(GM-LAMP)算法进行对比,结果表明:在估计精度方面,所提算法相对表现较好的深度学习算法LAMP、GM-LAMP分别提升约3.07和2.61 d B,较传统算法OMP、AMP分别提升约11.12和9.57 d B;在参数量方面,所提算法较LAMP、GM-LAMP分别减少约39%和69%。