A Parallel Learning Algorithm for Bayesian Inference Networks
A Parallel Learning Algorithm for Bayesian Inference Networks
复制标题
贝叶斯推理网络的并行学习算法
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
LamDepartment
中科院分区：
文献类型：
--
作者：
Wai;LamDepartment
提出了一种新的从数据中学习贝叶斯推理网络的并行算法。我们的学习算法利用了基于mdl的评分指标的特性，以及一种称为唠叨的分布式、异步、自适应搜索技术。唠叨本质上是容错的，具有动态负载平衡特性，并且伸缩性很好。我们通过在20台机器上进行的几个实验，实证地证明了我们方法的可行性、有效性和可扩展性。更具体地说，我们表明我们的分布式算法可以为更大的问题提供最佳解决方案，也可以为多达150个变量的贝叶斯网络提供良好的解决方案。
We present a new parallel algorithm for learning Bayesian inference networks from data. Our learning algorithm exploits both properties of the MDL-based score metric, and a distributed , asynchronous, adaptive search technique called nagging. Nagging is intrinsically fault tolerant, has dynamic load balancing features, and scales well. We demonstrate the viability, eeectiveness, and scalability of our approach empirically with several experiments using on the order of 20 machines. More speciically, we show that our distributed algorithm can provide optimal solutions for larger problems as well as good solutions for Bayesian networks of up to 150 variables.