Efficient Model Selection for Sparse Least-Square SVMs
| Autor: | Huanlai Xing, Xueqin Liu, Suxiang Qian, Xiao Lei Xia |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Computer Science::Machine Learning
Article Subject Computational complexity theory business.industry lcsh:Mathematics General Mathematics Model selection General Engineering Pattern recognition lcsh:QA1-939 Time cost Support vector machine Statistics::Machine Learning ComputingMethodologies_PATTERNRECOGNITION lcsh:TA1-2040 Computer Science::Sound Computer Science::Computer Vision and Pattern Recognition Regularization (physics) Artificial intelligence lcsh:Engineering (General). Civil engineering (General) business Mathematics |
| Zdroj: | Mathematical Problems in Engineering, Vol 2013 (2013) |
| ISSN: | 1563-5147 1024-123X |
| Popis: | The Forward Least-Squares Approximation (FLSA) SVM is a newly-emerged Least-Square SVM (LS-SVM) whose solution is extremely sparse. The algorithm uses the number of support vectors as the regularization parameter and ensures the linear independency of the support vectors which span the solution. This paper proposed a variant of the FLSA-SVM, namely, Reduced FLSA-SVM which is of reduced computational complexity and memory requirements. The strategy of “contexts inheritance” is introduced to improve the efficiency of tuning the regularization parameter for both the FLSA-SVM and the RFLSA-SVM algorithms. Experimental results on benchmark datasets showed that, compared to the SVM and a number of its variants, the RFLSA-SVM solutions contain a reduced number of support vectors, while maintaining competitive generalization abilities. With respect to the time cost for tuning of the regularize parameter, the RFLSA-SVM algorithm was empirically demonstrated fastest compared to FLSA-SVM, the LS-SVM, and the SVM algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|