arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1206.5291cs.LGcs.AIstat.ML
收藏

一种改进的置信传播动态调度算法

Improved Dynamic Schedules for Belief Propagation

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Charles Sutton, Andrew McCallum

摘要:

置信传播及其变体是用于近似推理的流行方法,但是它们的运行时间甚至它们的收敛性在很大程度上取决于用于发送消息的调度。最近,动态更新调度在硬网络上的收敛速度比静态调度快得多,即Elidan等人的剩余BP调度。但是RBP算法浪费了消息更新:许多消息的计算仅仅是为了确定它们的优先级,并且从未实际执行。在本文中,我们表明,估计残差,而不是直接计算它,导致收敛所需的消息数量显着减少,并在总运行时间。残差估计使用的上界的基础上最近的工作BP的消息错误。在合成和真实世界的网络中,这大大减少了BP的运行时间,在某些情况下减少了五倍,而不会影响解决方案的质量。

英文摘要:

Belief propagation and its variants are popular methods for approximate inference, but their running time and even their convergence depend greatly on the schedule used to send the messages. Recently, dynamic update schedules have been shown to converge much faster on hard networks than static schedules, namely the residual BP schedule of Elidan et al. [2006]. But that RBP algorithm wastes message updates: many messages are computed solely to determine their priority, and are never actually performed. In this paper, we show that estimating the residual, rather than calculating it directly, leads to significant decreases in the number of messages required for convergence, and in the total running time. The residual is estimated using an upper bound based on recent work on message errors in BP. On both synthetic and real-world networks, this dramatically decreases the running time of BP, in some cases by a factor of five, without affecting the quality of the solution.

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。

↑