A fast learning algorithm for One-Class Slab Support Vector Machines
This work addresses efficiency issues in machine learning for researchers and practitioners using one-class classification, but it is incremental as it builds on existing methods.
The paper tackles the problem of slow training for One-Class Slab Support Vector Machines by proposing a fast training method using an updated Sequential Minimal Optimization algorithm, resulting in better scalability to large datasets compared to other Quadratic Programming solvers.
One Class Slab Support Vector Machines (OCSSVM) have turned out to be better in terms of accuracy in certain classes of classification problems than the traditional SVMs and One Class SVMs or even other One class classifiers. This paper proposes fast training method for One Class Slab SVMs using an updated Sequential Minimal Optimization (SMO) which divides the multi variable optimization problem to smaller sub problems of size two that can then be solved analytically. The results indicate that this training method scales better to large sets of training data than other Quadratic Programming (QP) solvers.