Add to ORKGPerturbed generalised Taylor-like series are utilised to obtain approximations and bounds for divergence measures arising in Information Theory. In particular, the results are demonstrated for the estimate of the Kullback-Leubler distance, Shannon entropy and mutual information. Application to the Jeffreys divergence measure is also examined
Inferring and comparing complex, multivariable probability density functions is fundamental to probl...
Data science, information theory, probability theory, statistical learning, statistical signal proce...
Divergence measures are widely used in various applications of pattern recognition, signal processin...
Perturbed generalised Taylor-like series are utilised to obtain approximations and bounds for diverg...
[[abstract]]The problem of choosing a proper divergence measure is an important one. We provide new ...
Sharp bounds are obtained for perturbed generalised Taylor series. The perturbation involves the ari...
Sharp bounds are obtained for perturbed generalised Taylor series. The perturbation involves the ari...
Some new inequalities for the well-known Jeffreys divergence measure in Information Theory are given
In this work, we introduce new series of divergence measures as a family of Csiszar’s functional div...
The aim of this review is to give different two-parametric generalizations of the following measures...
Sharp bounds are obtained for perturbed generalised Taylor series. The perturbation involves the ari...
In this paper, we obtain certain bounds for some dynamic information divergences measures viz. Renyi...
In this paper, we obtain certain bounds for some dynamic information divergences measures viz. Renyi...
Information and Divergence measures deals with the study of problems concerning information processi...
Inferring and comparing complex, multivariable probability density functions is fundamental to probl...
Inferring and comparing complex, multivariable probability density functions is fundamental to probl...
Data science, information theory, probability theory, statistical learning, statistical signal proce...
Divergence measures are widely used in various applications of pattern recognition, signal processin...
Perturbed generalised Taylor-like series are utilised to obtain approximations and bounds for diverg...
[[abstract]]The problem of choosing a proper divergence measure is an important one. We provide new ...
Sharp bounds are obtained for perturbed generalised Taylor series. The perturbation involves the ari...
Sharp bounds are obtained for perturbed generalised Taylor series. The perturbation involves the ari...
Some new inequalities for the well-known Jeffreys divergence measure in Information Theory are given
In this work, we introduce new series of divergence measures as a family of Csiszar’s functional div...
The aim of this review is to give different two-parametric generalizations of the following measures...
Sharp bounds are obtained for perturbed generalised Taylor series. The perturbation involves the ari...
In this paper, we obtain certain bounds for some dynamic information divergences measures viz. Renyi...
In this paper, we obtain certain bounds for some dynamic information divergences measures viz. Renyi...
Information and Divergence measures deals with the study of problems concerning information processi...
Inferring and comparing complex, multivariable probability density functions is fundamental to probl...
Inferring and comparing complex, multivariable probability density functions is fundamental to probl...
Data science, information theory, probability theory, statistical learning, statistical signal proce...
Divergence measures are widely used in various applications of pattern recognition, signal processin...