Convolution Kernels on Discrete Structures

We introduce a new method of constructing kernels on sets whose elements are discrete structures like strings, trees and graphs. The method can be applied iteratively to build a kernel on a innnite set from kernels involving generators of the set. The family of kernels generated generalizes the family of radial basis kernels. It can also be used to deene kernels in the form of joint Gibbs probability distributions. Kernels can be built from hidden Markov random elds, generalized regular expressions, pair-HMMs, or ANOVA de-compositions. Uses of the method lead to open problems involving the theory of innnitely divisible positive deenite functions. Fundamentals of this theory and the theory of reproducing kernel Hilbert spaces are reviewed and applied in establishing the validity of the method.