Rigorous dynamics of expectation-propagation-based signal recovery from unitarily invariant measurements
Rigorous dynamics of expectation-propagation-based signal recovery from unitarily invariant measurements
复制标题
DOI：
10.1109/isit.2017.8006578
复制
发表时间：
2017-01
期刊：
影响因子：
--
通讯作者：
K. Takeuchi
中科院分区：
文献类型：
--
作者：
K. Takeuchi
本文研究了基于期望传播（EP）的酉不变测量稀疏信号恢复。在大系统极限下，对基于EP的消息传递算法的状态演化（SE）进行了严格的分析，其中输入和输出维数以相同的速度趋于无穷大.主要结果是证明了Ma和Ping提出的一个SE公式。
This paper investigates sparse signal recovery based on expectation propagation (EP) from unitarily invariant measurements. A rigorous analysis is presented for the state evolution (SE) of an EP-based message-passing algorithm in the large system limit, where both input and output dimensions tend to infinity at an identical speed. The main result is the justification of an SE formula conjectured by Ma and Ping.