The exponential family in abstract information theory
arXiv:1302.5205
Abstract
We introduce generalized notions of a divergence function and a Fisher information matrix. We propose to generalize the notion of an exponential family of models by reformulating it in terms of the Fisher information matrix. Our methods are those of information geometry. The context is general enough to include applications from outside statistics.
arXiv comment8 pages
References in corpus (6)
- Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
- The q-exponential family in statistical physics
- Estimators, escort probabilities, and phi-exponential families in statistical physics
- Exponential Families and MaxEnt Calculations for Entropy Measures of Statistical Physics
- Data Set Models and Exponential Families in Statistical Physics and Beyond
- Marginal Polytope of a Deformed Exponential Family