About distances of discrete distributions satisfying the data processing theorem of information theory

Authors:
M. C. Pardo;I. Vajda
Affiliations:
Sch. of Stat., Complutense Univ., Madrid;-
Venue:
IEEE Transactions on Information Theory
Year:
2006

Citing 0
Cited 5

Goodness-of-fit tests based on Rao's divergence under sparseness assumptions

Applied Mathematics and Computation
Rao's statistic for constant and proportional hazard models

Journal of Computational and Applied Mathematics
A study on invariance of f-divergence and its application to speech recognition

IEEE Transactions on Signal Processing
Pattern learning and recognition on statistical manifolds: an information-geometric review

SIMBAD'13 Proceedings of the Second international conference on Similarity-Based Pattern Recognition
Beyond differential privacy: composition theorems and relational logic for f-divergences between probabilistic programs

ICALP'13 Proceedings of the 40th international conference on Automata, Languages, and Programming - Volume Part II

Quantified Score

Hi-index	754.84

Visualization

Abstract

The distances of discrete probability distributions are considered. Necessary and sufficient conditions for validity of the data processing theorem of information theory are established. These conditions are applied to the Burbea-Rao (1982) divergences and Bregman (1967) distances