Universality of Approximate Message Passing Algorithms

Universality of Approximate Message Passing Algorithms
复制标题

DOI:
10.1214/21-ejp604
复制
发表时间:
2020-03
期刊:
ArXiv
影响因子:
--
通讯作者:
Wei-Kuo Chen;Wai-Kit Lam
Wei-Kuo Chen;Wai-Kit Lam
中科院分区:
其他
文献类型:
--
作者:
Wei-Kuo Chen;Wai-Kit Lam

文献摘要

相似文献

我们认为广泛的一类近似消息传递(AMP)算法定义为Lipschitz函数迭代的$n\times n$随机对称矩阵$A$。我们建立了普遍性的噪声为这个AMP的$n$-限制,并验证了这种行为在一些普遍适用于压缩传感,统计推断,优化自旋玻璃的AMP。
We consider a broad class of Approximate Message Passing (AMP) algorithms defined as a Lipschitzian functional iteration in terms of an $n\times n$ random symmetric matrix $A$. We establish universality in noise for this AMP in the $n$-limit and validate this behavior in a number of AMPs popularly adapted in compressed sensing, statistical inferences, and optimizations in spin glasses.