Peak criterion for choosing Gaussian kernel bandwidth in Support Vector Data Description

Support Vector Data Description (SVDD) is a machine learning technique used for single class classification and outlier detection. SVDD formulation with kernel function provides a flexible boundary around data. The value of kernel function parameters affects the nature of data boundary. For example, it is observed that with Gaussian kernel, as the value of kernel bandwidth is lowered, the data boundary changes from spherical to wiggly. The spherical data boundary leads to underfitting and extremely wiggly data boundary leads to overfitting. In this paper we propose an empirical criteria to obtain a good value of Gaussian kernel bandwidth which provides a smooth boundary capturing the essential visual features of the data.