Tuning SVM parameters by using a hybrid CLPSO–BFGS algorithm

Parameter settings of support vector machine (SVM) have a great influence on its performance. Grid search combining with cross-validation and numerical methods by minimizing some generalization error bounds are two usually adopted methods to tune the multiple parameters in SVM. However, the grid search is often time-consuming, especially when dealing with multiple parameters while the numerical methods are very sensitive to the initial value of the parameters. In this paper, we present a hybrid strategy to combine a comprehensive learning particle swarm optimizer (CLPSO) with Broyden–Fletcher–Goldfarb–Shanno (BFGS) method for effectively tuning the SVM parameters based on the generalization bounds. Rather than locating a single local optimum, the hybrid method can identify multiple local optima of the generalization bounds, which can greatly improve the stability of the parameter settings. The experimental results show that the proposed method can efficiently tune the parameters of both L1-SVM and L2-SVM and achieve competitive performance compared with other optimized classifiers.