Information Theoretic Proofs of Entropy Power Inequalities - IMT - Institut Mines-Télécom Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Information Theory Année : 2011

Information Theoretic Proofs of Entropy Power Inequalities

Résumé

While most useful information theoretic inequalities can be deduced from the basic properties of entropy or mutual information, up to now Shannon's entropy power inequality (EPI) is an exception: Existing information theoretic proofs of the EPI hinge on representations of differential entropy using either Fisher information or minimum mean-square error (MMSE), which are derived from de Bruijn's identity. In this paper, we first present an unified view of these proofs, showing that they share two essential ingredients: 1) a data processing argument applied to a covariance-preserving linear transformation; 2) an integration over a path of a continuous Gaussian perturbation. Using these ingredients, we develop a new and brief proof of the EPI through a mutual information inequality, which replaces Stam and Blachman's Fisher information inequality (FII) and an inequality for MMSE by Guo, Shamai and Verdú used in earlier proofs. The result has the advantage of being very simple in that it relies only on the basic properties of mutual information. These ideas are then generalized to various extended versions of the EPI: Zamir and Feder's generalized EPI for linear transformations of the random variables, Takano and Johnson's EPI for dependent variables, Liu and Viswanath's covariance-constrained EPI, and Costa's concavity inequality for the entropy power.
Fichier principal
Vignette du fichier
201101rioul.pdf (465.15 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00631353 , version 1 (12-10-2011)

Identifiants

  • HAL Id : hal-00631353 , version 1

Citer

O. Rioul. Information Theoretic Proofs of Entropy Power Inequalities. IEEE Transactions on Information Theory, 2011, 57 (1), pp.33-55. ⟨hal-00631353⟩
296 Consultations
1653 Téléchargements

Partager

Gmail Facebook X LinkedIn More