Fisher information matrix and hyperbolic geometry
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3 pp.
Abstract
The Fisher information matrix induces a metric on parametric spaces of families of probability density functions. We analyse here the family of normal distributions showing how hyperbolic geometry arises naturally from the Fisher information metric.Keywords
This publication has 9 references indexed in Scilit:
- Graphs, Tessellations, and Perfect Codes on Flat ToriIEEE Transactions on Information Theory, 2004
- The Fréchet mean shape and the shape of the meansAdvances in Applied Probability, 2000
- Extremal problems for conditioned brownian motion and the hyperbolic metricAnnales de l'institut Fourier, 2000
- Information and the Accuracy Attainable in the Estimation of Statistical Parameters1992
- Geometrically uniform codesIEEE Transactions on Information Theory, 1991
- Information theoretic inequalitiesIEEE Transactions on Information Theory, 1991
- On the similarity of the entropy power inequality and the Brunn- Minkowski inequality (Corresp.)IEEE Transactions on Information Theory, 1984
- The Geometry of Discrete Groups1983
- Entropy differential metric, distance and divergence measures in probability spaces: A unified approachJournal of Multivariate Analysis, 1982