In information geometry, the Fisher information metric is a particular Riemannian metric which can be defined on a smooth statistical manifold, i.e., a smooth manifold whose points are probability measures defined on a common probability space.

It can be used to calculate the informational difference between measurements. It takes the form:

g_{jk} = \int \frac{\partial \log p(x,\theta)}{\partial \theta_j} \frac{\partial \log p(x,\theta)}{\partial \theta_k} p(x,\theta) dx.

Substituting i = -\ln(p) from information theory, the formula becomes:

g_{jk} = \int \frac{\partial i(x,\theta)}{\partial \theta_j} \frac{\partial i(x,\theta)}{\partial \theta_k} p(x,\theta) dx.

Which can be thought of intuitively as: "The distance between two points on a statistical differential manifold is the amount of information between them, i.e. the informational difference between them."

An equivalent form of the above equation is:

g_{jk} = \int \frac{\partial^2 i(x,\theta)}{\partial \theta_j \partial \theta_k} p(x,\theta) dx = \mathrm{E} \left[ \frac{\partial^2 i(x,\theta)}{\partial \theta_j \partial \theta_k} \right].

See also

• Cramér-Rao bound
• Fisher information
• Bures metric

References

• Shun'ichi Amari - Differential-geometrical methods in statistics, Lecture notes in statistics, Springer-Verlag, Berlin, 1985.
• Shun'ichi Amari, Hiroshi Nagaoka - Methods of information geometry, Translations of mathematical monographs; v. 191, American Mathematical Society, 2000.