arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1402.3210cs.ITmath.IT
收藏

关于任意矩阵近似消息传递的收敛性

On the Convergence of Approximate Message Passing with Arbitrary Matrices

Sundeep Rangan, Philip Schniter, Alyson K. Fletcher, Subrata Sarkar

摘要:

近似消息传递(AMP)方法及其变体最近在估计通过线性变换$\mathbf{A}$观察到的随机向量$\mathbf{x}$的问题上吸引了相当多的关注。在大i.i.d.的情况下,零均值高斯$\mathbf{A}$,该方法表现出快速收敛与精确的分析表征的算法行为。然而,AMP在一般变换$\mathbf{A}$下的收敛性还没有完全理解。在本文中,我们提供了一个阻尼版本的广义AMP(GAMP)算法在二次成本函数(即,高斯似然和先验)。结果表明,有足够的阻尼,该算法是保证收敛,虽然阻尼量的增长与峰均比的平方奇异值的变换$\mathbf{A}$。这一结果解释了AMP在i.i.d.上的良好性能。高斯变换$\mathbf{A}$,但也有他们的困难与病态或非零均值变换$\mathbf{A}$。在一般的代价函数下,假设一定的严格凸性条件,导出了阻尼GAMP方法局部稳定性的一个充分条件。

英文摘要:

Approximate message passing (AMP) methods and their variants have attracted considerable recent attention for the problem of estimating a random vector $\mathbf{x}$ observed through a linear transform $\mathbf{A}$. In the case of large i.i.d. zero-mean Gaussian $\mathbf{A}$, the methods exhibit fast convergence with precise analytic characterizations on the algorithm behavior. However, the convergence of AMP under general transforms $\mathbf{A}$ is not fully understood. In this paper, we provide sufficient conditions for the convergence of a damped version of the generalized AMP (GAMP) algorithm in the case of quadratic cost functions (i.e., Gaussian likelihood and prior). It is shown that, with sufficient damping, the algorithm is guaranteed to converge, although the amount of damping grows with peak-to-average ratio of the squared singular values of the transforms $\mathbf{A}$. This result explains the good performance of AMP on i.i.d. Gaussian transforms $\mathbf{A}$, but also their difficulties with ill-conditioned or non-zero-mean transforms $\mathbf{A}$. A related sufficient condition is then derived for the local stability of the damped GAMP method under general cost functions, assuming certain strict convexity conditions.

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。

↑