0


符号图上信仰传播的唯一性

Uniqueness of Belief Propagation on Signed Graphs
课程网址: http://videolectures.net/nips2011_watanabe_graphs/  
主讲教师: Yusuke Watanabe
开课单位: 统计数学研究所
开课时间: 2012-09-06
课程语种: 英语
中文简介:
虽然循环信念传播(lbp)已被广泛应用于各种应用中,并取得了经验上的成功,但它几乎没有理论上的保证。特别是,如果图形模型中随机变量的交互作用很强,由于潜在的相变,该算法的行为很难分析。本文提出了一种新的LBP不动点唯一性问题的解决方法,即用图形和符号来描述新的“必要和充分”条件,其中符号表示边缘上的相互作用(即相容函数)的类型(吸引/排斥)。在所有之前的作品中,只有在交互的强度在某种意义上“足够小”的情况下,才能保证独特性。相反,我们的条件涵盖了指定类有符号图上的任意强交互。本文的结果是基于LBP算法的最新理论进展,以及与图zeta函数的联系。
课程简介: While loopy Belief Propagation (LBP) has been utilized in a wide variety of applications with empirical success, it comes with few theoretical guarantees. Especially, if the interactions of random variables in a graphical model are strong, the behaviors of the algorithm can be difficult to analyze due to underlying phase transitions. In this paper, we develop a novel approach to the uniqueness problem of the LBP fixed point; our new “necessary and sufficient” condition is stated in terms of graphs and signs, where the sign denotes the types (attractive/repulsive) of the interaction (i.e., compatibility function) on the edge. In all previous works, uniqueness is guaranteed only in the situations where the strength of the interactions are “sufficiently” small in certain senses. In contrast, our condition covers arbitrary strong interactions on the specified class of signed graphs. The result of this paper is based on the recent theoretical advance in the LBP algorithm; the connection with the graph zeta function.
关 键 词: 信仰传播; 随机变量; 唯一性; 相互作用
课程来源: 视频讲座网
最后编审: 2020-06-06:zyk
阅读次数: 63