求解线性系统的消息传递算法的收敛速度
Convergence Rate of a Message-passing Algorithm for Solving Linear Systems
摘要:
研究了求解大型线性系统的消息传递分布式算法的收敛速度。这个问题是从著名的高斯置信传播(BP)问题的统计学习和分布式信号处理,和这个消息传递算法是从著名的高斯BP算法推广。广义对角优势的假设下,我们揭示,通过艰苦的推导,消息传递算法的收敛速度上的几个界限。特别是,我们清楚地表明,如何使用系统的对角优势的算法的收敛速度可以显式有界。当专门针对高斯BP问题时,我们的工作还为BP算法的行为提供了新的理论见解,因为我们使用纯线性代数方法进行收敛分析。
英文摘要:
This paper studies the convergence rate of a message-passing distributed algorithm for solving a large-scale linear system. This problem is generalised from the celebrated Gaussian Belief Propagation (BP) problem for statistical learning and distributed signal processing, and this message-passing algorithm is generalised from the well-celebrated Gaussian BP algorithm. Under the assumption of generalised diagonal dominance, we reveal, through painstaking derivations, several bounds on the convergence rate of the message-passing algorithm. In particular, we show clearly how the convergence rate of the algorithm can be explicitly bounded using the diagonal dominance properties of the system. When specialised to the Gaussian BP problem, our work also offers new theoretical insight into the behaviour of the BP algorithm because we use a purely linear algebraic approach for convergence analysis.
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。