Probabilistic Methods for Support Vector Machines
Peter Sollich · 1999
I describe a framework for interpreting Support Vector Machines (SVMs) as maximum a posteriori (MAP) solutions to inference problems with Gaussian Process priors. This can provide intuitive guidelines for choosing a `good' SVM kernel. It can also assign (by evidence maximization) optimal values to parameters such as the noise level C which cannot be determined unambiguously from properties of the MAP solution alone (such as cross-validation error) . I illustrate this using a simple approximate expression for the SVM evidence. Once C has been determined, error bars on SVM predictions can also be obtained. 1 Support Vector Machines: A probabilistic framework Support Vector Machines (SVMs) have recently been the subject of intense research activity within the neural networks community; for tutorial introductions and overviews of recent developments see [1, 2, 3]. One of the open questions that remains is how to set the `tunable' parameters of an SVM algorithm: While methods for...