Fast Kernel-based Method for Anomaly Detection

Anomaly detection (AD) involves detecting abnormality from normality and has a wide spectrum of applications in reality. Kernel-based methods for AD have been proven robust with diverse data distributions and offering good generalization ability. Stochastic gradient descent (SGD) method has recently emerged as a promising framework to devise ultra-fast learning methods. In this paper, we conjoin the advantages of Kernel-based method and SGD-based method to propose fast learning methods for anomaly detection. We validate the proposed methods on 8 benchmark datasets in UCI repository and KDD cup 1999 dataset. The experimental results show that the proposed methods offer a comparable one-class classification accuracy while simultaneously achieving a significantly computational speed-up.