Fisher information metric and Poisson kernels

String Kernels , Fisher Kernels

In this paper we show how the generation of documents can be thought of as a k-stage Markov process, which leads to a Fisher kernel from which the n-gram and string kernels can be reconstructed. The Fisher kernel view gives a more exible insight into the string kernel and suggests how it can be parametrised in a way that re-ects the statistics of the training corpus. Furthermore, the prob-abili...

Dynamics of the Fisher information metric.

We present a method to generate probability distributions that correspond to metrics obeying partial differential equations generated by extremizing a functional J [g(mu nu) (theta(i)) ] , where g(mu nu) (theta(i)) is the Fisher metric. We postulate that this functional of the dynamical variable g(mu nu) (theta(i)) is stationary with respect to small variations of these variables. Our approach ...

Reproducing kernels , Bergman kernels , Poisson kernels

Learning Discriminative Fisher Kernels

Fisher kernels provide a commonly used vectorial representation of structured objects. The paper presents a technique that exploits label information to improve the object representation of Fisher kernels by employing ideas from metric learning. In particular, the new technique trains a generative model in such a way that the distance between the log-likelihood gradients induced by two objects ...

Relations between Renyi Distance and Fisher Information

In this paper, we first show that Renyi distance between any member of a parametric family and its perturbations, is proportional to its Fisher information. We, then, prove some relations between the Renyi distance of two distributions and the Fisher information of their exponentially twisted family of densities. Finally, we show that the partial ordering of families induced by Renyi dis...