Extreme symmetry and the directed divergence in information theory
Factorized mutual information maximization
We investigate the sets of joint probability distributions that maximize the average multi-information over a collection of margins. These functionals serve as proxies for maximizing the multi-information of a set of variables or the mutual information of two subsets of variables, at a lower computation and estimation complexity. We describe the maximizers and their relations to the maximizers of the multi-information and the mutual information.
Fluctuations of the empirical entropies of a chain of infinite order.
Funciones de entropía asociadas a medidas de Csiszar.
En este trabajo se presentan las medidas de entropía que provienen de la distancia, en el sentido de Csiszar, entre una distribución y la distribución en la que todos los sucesos son equiprobables. En segundo lugar, se estudian condiciones para la concavidad y no negatividad de las medidas propuestas. Finalmente, se obtienen los funcionales Φ-entropía como casos particulares de las medidas estudiadas.
Functional equations and information measures with preference
Functional equations related to non-additive information measures
Fundamental equation of information revisited.
Further reverse results for Jensen's discrete inequality and applications in information theory.
Fuzzified Blackwell's method to compare experiments
Fuzzy information and combinatorial inequalities
Gaussian maximum of entropy and reversed log-Sobolev inequality
Generalised directed divergence without symmetry
Generalization of sum representation functional equations. I.
Generalization of sum representation functional equations. II: Generalized directed divergence
Generalization of the non-additive measures of uncertainty and information and their axiomatic characterizations
Generalized characteristic equation of branching information measures.
Generalized Entropies in Coding Theory.
Generalized fundamental equation of information of multiplicative type.
Generalized information criteria for Bayes decisions
This paper deals with Bayesian models given by statistical experiments and standard loss functions. Bayes probability of error and Bayes risk are estimated by means of classical and generalized information criteria applicable to the experiment. The accuracy of the estimation is studied. Among the information criteria studied in the paper is the class of posterior power entropies which include the Shannon entropy as special case for the power . It is shown that the most accurate estimate is in this...
Generalized Jensen difference based on entropy functions