论文信息 - Nested Buffer SMO Algorithm for Training Support Vector Classifiers

Nested Buffer SMO Algorithm for Training Support Vector Classifiers

This paper presents a new decomposition algorithm for training support vector classifiers. The algorithm uses the analytical quadratic programming (QP) solver proposed in sequential minimal optimization (SMO) as its core solver. The new algorithm is featured by a nested buffer structure, which serves as a working set selection system. This system can achieve faster convergence by imposing restriction on the scope of working set selection. More efficient kernel cache utilization and more economical cache shape are additional benefits, which make the algorithm even faster. Experiments on various problems show that the new algorithm is 1.51 times as fast as LibSVM on average.

Xiang Wu | Wenkai Lu

[1] V. Vapnik. Estimation of Dependences Based on Empirical Data , 2006 .

[2] Bo Zhang,et al. A new strategy for selecting working sets applied in SMO , 2002, Object recognition supported by user interaction for service robots.

[3] Vladimir Vapnik,et al. Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics) , 1982 .

[4] Federico Girosi,et al. Support Vector Machines: Training and Applications , 1997 .

[5] Thorsten Joachims,et al. Making large-scale support vector machine learning practical , 1999 .

[6] S. Sathiya Keerthi,et al. Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[8] J. Platt. Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[9] Christopher J. C. Burges,et al. A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.