Measure and probability theory
In information geometry, a (Fisher-)information metric is a Riemannian metric on a manifold of probability distributions over some probability space (the latter often assumed to be finite).
On a finite probability space Set a positive measure is a function and a probability distribution is one such that .
This space is actually a submanifold of . For the canonical basis of tangent vectors on this wedge of Cartesian space, the information metric is given by
- L. L. Campbell, An extended Čencov characterization of the information metric Journal: Proc. Amer. Math. Soc. 98 (1986), 135-141. (AMS)
Created on June 17, 2011 17:48:10
by Urs Schreiber