Sparse Bayesian kernel logistic regression

In this paper we present a simple hierarchical Bayesian treatment of the sparse kernel logistic regression (KLR) model based MacKay's evidence approximation. The model is re-parameterised such that an isotropic Gaussian prior over parameters in the kernel induced feature space is replaced by an isotropic Gaussian prior over the transformed parameters, facilitating a Bayesian analysis using standard methods. The Bayesian approach allows the selection of "good" values for the usual regularisation and kernel parameters through maximisation of the marginal likelihood. Results obtained on a variety of benchmark datasets are provided indicating that the Bayesian kernel logistic regression model is competitive, whilst having one less parameter to determine during model selection.

• Type: Conference
• Year: 2004
• Where: ESANN
• Authors: Gavin C. Cawley, Nicola L. C. Talbot
• Keywords: ESANN 2004, ESANN 2007, Hierarchical Bayesian Treatment, Kernel Induced Feature, Kernel Logistic Regression