Parallel sequential minimal optimization for the training of support vector machines
Parallel sequential minimal optimization for the training of support vector machines
复制标题
支持向量机训练的并行顺序最小优化
DOI：
10.1109/tnn.2006.875989
复制
发表时间：
2006-07-01
影响因子：
--
通讯作者：
Lee, H. P.
中科院分区：
文献类型：
--
作者：
Cao, L. J.;Keerthi, S. S.;Lee, H. P.
序贯最小优化（SMO）是一种常用的支持向量机（SVM）训练算法，但在求解大规模问题时仍需要大量的计算时间。本文提出了一种并行实现SMO训练SVM。采用消息传递接口（MPI）开发了并行SMO。具体来说，并行SMO首先将整个训练数据集划分为较小的子集，然后同时运行多个CPU处理器来处理每个分区的数据集。实验表明，在成人数据集和混合国家标准与技术研究所（MNIST）的数据集，有很大的加速比时，使用多个处理器。在网络数据集上也有令人满意的结果。
Sequential minimal optimization (SMO) is one popular algorithm for training support vector machine (SVM), but it still requires a large amount of computation time for solving large size problems. This paper proposes one parallel implementation of SMO for training SVM. The parallel SMO is developed using message passing interface (MPI). Specifically, the parallel SMO first partitions the entire training data set into smaller subsets and then simultaneously runs multiple CPU processors to deal with each of the partitioned data sets. Experiments show that there is great speedup on the adult data set and the Mixing National Institute of Standard and Technology (MNIST) data set when many processors are used. There are also satisfactory results on the Web data set.