Information geometry on hierarchy of probability distributions

IEEE Transactions on Information Theory

Volumn 47, Issue 5, 2001, Pages 1701-1711

  Amari, S I ^a  

^a RIKEN BRAIN SCIENCE INSTITUTE   (Japan)

Author keywords

Decomposition of entropy; e and m projections; Extended Pythagoras theorem; Higher order interactions; Higher order Markov chain; Information geometry; Kullback divergence

Indexed keywords

CORRELATION METHODS; HIERARCHICAL SYSTEMS; MARKOV PROCESSES; PROBABILITY DENSITY FUNCTION; RANDOM PROCESSES; THEOREM PROVING; VECTORS;

INFORMATION GEOMETRY; PYTHAGORAS THEOREM;

PROBABILITY DISTRIBUTIONS;

EID: 0035397522     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/18.930911     Document Type: Article

References (38)

1. Dynamics of neuronal firing correlation: Modulation of 'effective connectivity'
2. Differential geometry of a parametric family of invertible linear systems - Riemannian metric, dual affine connections and divergence
3. Fisher information under restriction of Shannon information
4. Dualistic geometry of the manifold of higher-order neurons
5. Information geometry of the EM and em algorithms for neural networks
6. Information geometry
7. Natural gradient works efficiently in learning
8. Information geometry of α-projection in mean-field approximation
9. Statistical inference under multi-terminal rate restrictions - A differential geometrical approach
10. Information geometry of estimating functions in semi parametric statistical models
11. Information geometry of Boltzmann machines
12. Mean-field methods for stochastic connections networks
13. The relation between information theory and the differential geometric approach to statistics
14. On topological properties of f-divergence
15. I-divergence geometry of probability distributions and minimization problems
16. Conditional limit theorems under Markov conditioning
17. Nonnegative entropy measures of multivariate symmetric correlations
18. Statistical inference under multiterminal data compression
19. Model dependence in quantification of spike interdependence by joint peri-stimulus time histogram
20. On the rationale of maximum entropy methods
21. Dualistic differential geometry of positive definite matrices and its applications to related problems
22. Information geometric analysis of an interior point method for semidefinite programming
23. On the significance of correlations among neuronal spike trains
24. An infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
25. The exponential statistical manifold: Mean parameters, orthogonality, and space transformation
26. Information and accuracy attainable in the estimation of statistical parameters
27. Information geometry of mean field approximation