首页军事学
0


飞溅的信念传播:通过异步调度的并行效率

Splash Belief Propagation: Efficient Parallelization Through Asynchronous Scheduling
课程网址: http://videolectures.net/nipsworkshops09_gonzalez_sbpe/  
主讲教师: Joseph Gonzalez
开课单位: 卡内基梅隆大学
开课时间: 2010-01-19
课程语种: 英语
中文简介:
在这项工作中, 我们集中在近似并行推理中的环图形模型使用环实信念传播。我们证明了信念传播的自然、完全同步的并行化效率很低。通过在链式图形模型上实现的环信念传播的可实现并行性能, 我们对信念传播的并行局限性进行了理论理解。然后介绍了 splash 信念传播, 这是一种并行的异步方法, 它实现了最优边界, 并在大型图形模型上演示了线性到超线性的缩放。最后, 我们讨论了如何将这些想法推广到并行迭代图形算法的上下文中, 我们的新图形实验室框架。
课程简介: In this work we focus on approximate parallel inference in loopy graphical models using loopy belief propagation. We demonstrate that the natural, fully synchronous parallelization of belief propagation is highly inefficient. By bounding the achievable parallel performance of loopy belief propagation on chain graphical models we develop a theoretical understanding of the parallel limitations of belief propagation. We then introduce Splash belief propagation, a parallel asynchronous approach which achieves the optimal bounds and demonstrates linear to super-linear scaling on large graphical models. Finally we discuss how these ideas may be generalized to parallel iterative graph algorithms in the context of our new GraphLab framework.
关 键 词: 空军基地; 飞溅的信念传播; 异步调度
课程来源: 视频讲座网
最后编审: 2020-06-22:chenxin
阅读次数: 61