Kernel Path for nu-Support Vector Classification

Document Type


Publication Title

IEEE Transactions on Neural Networks and Learning Systems


It is well known that the performance of a kernel method is highly dependent on the choice of kernel parameter. However, existing kernel path algorithms are limited to plain support vector machines (SVMs), which has one equality constraint. It is still an open question to provide a kernel path algorithm to nu-support vector classification (nu-SVC) with more than one equality constraint. Compared with plain SVM, nu-SVC has the advantage of using a regularization parameter nu for controlling the number of support vectors and margin errors. To address this problem, in this article, we propose a kernel path algorithm (KP nu SVC) to trace the solutions of nu-SVC exactly with respect to the kernel parameter. Specifically, we first provide an equivalent formulation of nu-SVC with two equality constraints, which can avoid possible conflicts during tracing the solutions of nu-SVC. Based on this equivalent formulation of nu-SVC, we propose the KP nu SVC algorithm to trace the solutions with respect to the kernel parameter. However, KP nu SVC traces nonlinear solutions of kernel method rather than the errors of loss function, and it is still a challenge to provide the algorithm that guarantees to find the global optimal model. To address this challenging problem, we extend the classical error path algorithm to the nonlinear kernel solution paths and propose a new kernel error path (KEP) algorithm that ensures to find the global optimal kernel parameter by minimizing the cross validation error. We also provide the finite convergence analysis and computational complexity analysis to KP nu SVC and KEP. Extensive experimental results on a variety of benchmark datasets not only verify the effectiveness of KP nu SVC but also show the advantage of applying KEP to select the optimal kernel parameter.



Publication Date



Kernel, Static VAr compensators, Support vector machines, Computational modeling, Training, Analytical models, Machine learning algorithms, Kernel path, model selection, piecewise non-linear, support vector machine (SVM)


IR Conditions:

OA version (pathway a): Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged