.png){kind=icon}
返回
Learning a compressive sensing matrix with structural constraints via maximum mean discrepancy optimization
.png){kind=icon}
OA
AI
DOI：10.1016/j.sigpro.2022.108553.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We introduce a learning-based algorithm to obtain a measurement matrix for compressive sensing re-lated recovery problems. The focus lies on matrices with a constant modulus constraint which, e.g., rep-resent a network of analog phase shifters in hybrid precoding/combining architectures. We interpret a matrix with restricted isometry property as a mapping from a high-to a low-dimensional hypersphere. We argue that points on the low-dimensional hypersphere should be uniformly distributed to combat measurement noise. This notion is formalized as an optimization problem which uses a maximum mean discrepancy metric as objective function. Recent success of such metrics in neural network related top-ics motivate a solution of the optimization problem based on machine learning. Numerical experiments show a better performance than random matrices that are typical for compressive sensing. Further, we adapt a method from the literature to the constant modulus constraint. This method can also compete with random matrices and harmonizes well with the proposed algorithm if it is used as an initialization. Lastly, we describe how other structural matrix constraints, e.g., a Toeplitz constraint, can be taken into account as well.(c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Compressive sensing
Machine learning
Maximum mean discrepancy
Restricted isometry property
Sparse channel estimation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
10.0K
被引数:
1.7W
机构
引用论文
1,1,3,3-tetramethyl-2-methyleneindan derivatives: syntheses with imminent rearrangement.png)
Tetrahedron
TetrahedronIF0
PREAI
分享收藏Indirect micro-scale method for the determination of desferrioxamine and its aluminium and iron chelated forms in biological samples by atomic absorption spectrometry with electrothermal atomisationThe Analyst
The AnalystIF0
PREAI
分享收藏Millimeter Wave Mobile Communications for 5G Cellular: It Will Work!5g蜂窝的毫米波移动通信: 它将起作用!IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Exploring the Exhaust Emission and Efficiency of Algal Biodiesel Powered Compression Ignition Engine: Application of Box–Behnken and Desirability Based Multi-Objective Response Surface MethodologyEnergiesOAAI
EnergiesIF0
OAAI分享收藏
查看更多内容