arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1001.3448cs.ITcs.LGmath.ITmath.STstat.TH
收藏

稠密图上消息传递的动力学及其在压缩感知中的应用

The dynamics of message passing on dense graphs, with applications to compressed sensing

Stanford University(斯坦福大学)

Mohsen Bayati, Andrea Montanari

摘要:

近似消息传递算法被证明是非常有效的重建稀疏信号从少量的非相干线性测量。大量的数值实验进一步表明,他们的动态准确地跟踪一个简单的一维迭代称为状态演化。在本文中,我们提供了第一个严格的基础状态演化。我们证明,它确实持有渐近的大系统极限的独立和同分布的高斯项的传感矩阵。虽然我们的重点是压缩感知的消息传递算法,分析扩展到这个设置之外,到稠密图上的一般类算法。在这种情况下,状态演化扮演的角色,密度演化稀疏图。证明技术与密度演化的标准方法有根本的不同,因为它处理了底层因子图中的大量短循环。相反,它依赖于最近由Erwin Bolthausen在自旋玻璃理论的背景下开发的条件反射技术。

英文摘要:

Approximate message passing algorithms proved to be extremely effective in reconstructing sparse signals from a small number of incoherent linear measurements. Extensive numerical experiments further showed that their dynamics is accurately tracked by a simple one-dimensional iteration termed state evolution. In this paper we provide the first rigorous foundation to state evolution. We prove that indeed it holds asymptotically in the large system limit for sensing matrices with independent and identically distributed gaussian entries. While our focus is on message passing algorithms for compressed sensing, the analysis extends beyond this setting, to a general class of algorithms on dense graphs. In this context, state evolution plays the role that density evolution has for sparse graphs. The proof technique is fundamentally different from the standard approach to density evolution, in that it copes with large number of short loops in the underlying factor graph. It relies instead on a conditioning technique recently developed by Erwin Bolthausen in the context of spin glass theory.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑