arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/0508070cs.ITcs.AImath.IT
收藏

通过(超)树上的一致性估计MAP:消息传递和线性规划

MAP estimation via agreement on (hyper)trees: Message-passing and linear programming

Martin J. Wainwright, Tommi S. Jaakkola, Alan S. Willsky

摘要:

我们开发和分析的方法计算证明最佳的{ \em最大后验}(MAP)配置的一个子类的马尔可夫随机场定义的图与周期。通过将原始分布分解为树结构分布的凸组合,我们获得了原始问题的最优值的上界(即,MAP分配的对数概率)。我们证明了这个上界是紧的,当且仅当所有的树分布共享一个共同的最优配置。一个重要的含义是,任何这样的共享配置也必须是原始分发的MAP配置。接下来,我们开发了两种方法来尝试获得严格的上界:(a){ \em树松弛线性规划}(LP),它是从上界的拉格朗日对偶推导出来的;和(b)一个{ \em树重新加权的最大积消息传递算法},它与最大积算法相关但不同。通过这种方式,我们建立了一定的LP松弛的模式发现问题之间的连接,并重新加权形式的最大产品(最小和)的消息传递算法。

英文摘要:

We develop and analyze methods for computing provably optimal {\em maximum a posteriori} (MAP) configurations for a subclass of Markov random fields defined on graphs with cycles. By decomposing the original distribution into a convex combination of tree-structured distributions, we obtain an upper bound on the optimal value of the original problem (i.e., the log probability of the MAP assignment) in terms of the combined optimal values of the tree problems. We prove that this upper bound is tight if and only if all the tree distributions share an optimal configuration in common. An important implication is that any such shared configuration must also be a MAP configuration for the original distribution. Next we develop two approaches to attempting to obtain tight upper bounds: (a) a {\em tree-relaxed linear program} (LP), which is derived from the Lagrangian dual of the upper bounds; and (b) a {\em tree-reweighted max-product message-passing algorithm} that is related to but distinct from the max-product algorithm. In this way, we establish a connection between a certain LP relaxation of the mode-finding problem, and a reweighted form of the max-product (min-sum) message-passing algorithm.

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。

↑