快速训练支持向量机的并行结构

Fast Training Support Vector Machines Using Parallel Architecture

序列最小优化(SMO)是一种常见的训练支持向量机(SVM)的算法,但在求解大规模问题时,它需要耗费大量的计算时间。文章提供SMO的一种并行实现方法。并行SMO是利用信息传递接口(MPI)开发的。首先将整个训练数据集分为多个小的子集,然后同时运行多个CPU处理器处理每一个分离的数据集。实验结果表明,当采用多处理器时,在Adult数据集上并行SMO有较大的加速比。

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 greater speedup on the adult data set data set when many processors are used.