To improve energy efficiency and spectral efficiency, massive multiple-input-multiple-output (MIMO) is proposed and becomes a promising technology in the next generation mobile communication. However, massive MIMO sys...
详细信息
To improve energy efficiency and spectral efficiency, massive multiple-input-multiple-output (MIMO) is proposed and becomes a promising technology in the next generation mobile communication. However, massive MIMO systems equip with scores of or hundreds of antennas which induce large-scale matrix computations with tremendous complexity, especially for matrix inversion in data detection. Thus, many detection methods have been proposed using approximate matrix inversion algorithms, which satisfy the demand of precision with low complexity. In this study, the authors focus on the approximate detection method based on Newton iteration (NI), and propose upgraded methods named NI method with iterative refinement (NIIR) and diagonal band NIIR (DBNIIR) which combine NI method and DBNI method with iterative refinement (IR). The results show that their proposals provide about 2 dB improvement on bit error rate (BER) for 16-quadrature amplitude modulation (QAM), and could even break the error floor existing in NI and DBNI methods for 64-QAM modulation. Furthermore, the BER of their proposals could provide almost the same performance as the exact method. Moreover, in contrast with NI and DBNI methods, NIIR and DBNIIR methods require quite few extra complexity cost and no extra hardware resource which is quite suitable for data detection in massive MIMO.
The CUR matrix decomposition and the Nystrom approximation are two important low-rank matrix approximation techniques. The Nystrom method approximates a symmetric positive semidefinite matrix in terms of a small numbe...
详细信息
The CUR matrix decomposition and the Nystrom approximation are two important low-rank matrix approximation techniques. The Nystrom method approximates a symmetric positive semidefinite matrix in terms of a small number of its columns, while CUR approximates an arbitrary data matrix by a small number of its columns and rows. Thus, CUR decomposition can be regarded as an extension of the Nystrom approximation. In this paper we establish a more general error bound for the adaptive column/row sampling algorithm, based on which we propose more accurate CUR and Nystrom algorithms with expected relative-error bounds. The proposed CUR and Nystrom algorithms also have low time complexity and can avoid maintaining the whole data matrix in RAM. In addition, we give theoretical analysis for the lower error bounds of the standard Nystrom method and the ensemble Nystrom method. The main theoretical results established in this paper are novel, and our analysis makes no special assumption on the data matrices.
The CUR matrix decomposition and the Nyström approximation are two important low-rank matrix approximation techniques. The Nyström method approximates a symmetric positive semidefinite matrix in terms of a s...
详细信息
The CUR matrix decomposition and the Nyström approximation are two important low-rank matrix approximation techniques. The Nyström method approximates a symmetric positive semidefinite matrix in terms of a small number of its columns, while CUR approximates an arbitrary data matrix by a small number of its columns and rows. Thus, CUR decomposition can be regarded as an extension of the Nyström *** this paper we establish a more general error bound for the adaptive column/row sampling algorithm, based on which we propose more accurate CUR and Nyström algorithms with expected relative-error bounds. The proposed CUR and Nyström algorithms also have low time complexity and can avoid maintaining the whole data matrix in RAM. In addition, we give theoretical analysis for the lower error bounds of the standard Nyström method and the ensemble Nyström method. The main theoretical results established in this paper are novel, and our analysis makes no special assumption on the data matrices.
暂无评论