arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1611.02010stat.MLcs.ITmath.IT
收藏

向量值高斯置信传播分布式推理的收敛性分析

Convergence Analysis of Distributed Inference with Vector-Valued Gaussian Belief Propagation

Jian Du, Shaodan Ma, Yik-Chung Wu, Soummya Kar, José M. F. Moura

摘要:

利用因子图和高斯置信传播(BP)研究分布式线性高斯模型的推理问题。分布式推理算法只涉及信息矩阵和平均向量的本地计算,以及邻居之间的消息传递。在较宽的条件下,证明了对于任意半正定初始化,消息信息矩阵收敛到唯一的正定极限矩阵,并且以双指数速率逼近该极限矩阵的任意小邻域.在消息信息矩阵初始化为半正定矩阵的假设下,给出了置信均值向量收敛于最优集中估计的充要条件.此外,它表明,高斯BP总是收敛时,底层的因子图是由森林和一个单一的循环的工会。所提出的分布式线性高斯模型的设置中的收敛条件被证明是严格弱于其他现有的收敛条件和要求,包括高斯马尔可夫随机场为基础的行走求和条件,并适用于一个大类的场景。

英文摘要:

This paper considers inference over distributed linear Gaussian models using factor graphs and Gaussian belief propagation (BP). The distributed inference algorithm involves only local computation of the information matrix and of the mean vector, and message passing between neighbors. Under broad conditions, it is shown that the message information matrix converges to a unique positive definite limit matrix for arbitrary positive semidefinite initialization, and it approaches an arbitrarily small neighborhood of this limit matrix at a doubly exponential rate. A necessary and sufficient convergence condition for the belief mean vector to converge to the optimal centralized estimator is provided under the assumption that the message information matrix is initialized as a positive semidefinite matrix. Further, it is shown that Gaussian BP always converges when the underlying factor graph is given by the union of a forest and a single loop. The proposed convergence condition in the setup of distributed linear Gaussian models is shown to be strictly weaker than other existing convergence conditions and requirements, including the Gaussian Markov random field based walk-summability condition, and applicable to a large class of scenarios.

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。

↑