arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1301.6295cs.ITmath.IT
收藏

任意矩阵广义近似消息传递的不动点

Fixed Points of Generalized Approximate Message Passing with Arbitrary Matrices

Sundeep Rangan, Philip Schniter, Erwin Riegler, Alyson Fletcher, Volkan Cevher

摘要:

通过线性变换,然后通过分量(可能是非线性的)输出映射的独立分量的随机向量的估计出现在一系列应用中。近似消息传递(AMP)方法,基于高斯近似的循环信念传播,最近引起了相当大的关注,这样的问题。对于大的随机变换,这些方法表现出快速收敛,并承认精确的分析特征与可测试的条件,即使是某些非凸问题的情况下,最优性。然而,AMP在一般变换下的行为还没有完全理解。在本文中,我们认为广义AMP(GAMP)算法和更常见的优化技术的方法。这种分析使GAMP算法的固定点,适用于任意变换的精确表征。特别是,我们表明,所谓的最大和GAMP算法的MAP估计的不动点的约束最大化的后验密度的临界点。和积GAMP算法估计后边缘的不动点可以解释为某个自由能的临界点。

英文摘要:

The estimation of a random vector with independent components passed through a linear transform followed by a componentwise (possibly nonlinear) output map arises in a range of applications. Approximate message passing (AMP) methods, based on Gaussian approximations of loopy belief propagation, have recently attracted considerable attention for such problems. For large random transforms, these methods exhibit fast convergence and admit precise analytic characterizations with testable conditions for optimality, even for certain non-convex problem instances. However, the behavior of AMP under general transforms is not fully understood. In this paper, we consider the generalized AMP (GAMP) algorithm and relate the method to more common optimization techniques. This analysis enables a precise characterization of the GAMP algorithm fixed-points that applies to arbitrary transforms. In particular, we show that the fixed points of the so-called max-sum GAMP algorithm for MAP estimation are critical points of a constrained maximization of the posterior density. The fixed-points of the sum-product GAMP algorithm for estimation of the posterior marginals can be interpreted as critical points of a certain free energy.

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。

↑