Skip to Main content Skip to Navigation
Conference papers

Rényi Entropy Power and Normal Transport

Olivier Rioul 1, 2
1 COMNUM - Communications Numériques
LTCI - Laboratoire Traitement et Communication de l'Information
Abstract : A framework for deriving Rényi entropy-power inequalities (REPIs) is presented that uses linearization and an inequality of Dembo, Cover, and Thomas. Simple arguments are given to recover the previously known Rényi EPIs and derive new ones, by unifying a multiplicative form with constant c and a modification with exponent α of previous works. An information-theoretic proof of the Dembo-Cover-Thomas inequality-equivalent to Young's convolutional inequality with optimal constants-is provided, based on properties of Rényi conditional and relative entropies and using transportation arguments from Gaussian densities. For log-concave densities, a transportation proof of a sharp varentropy bound is presented. This work was partially presented at the 2019 Information Theory and Applications Workshop, San Diego, CA.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.telecom-paris.fr/hal-02950168
Contributor : Olivier Rioul <>
Submitted on : Sunday, September 27, 2020 - 1:33:16 PM
Last modification on : Wednesday, September 30, 2020 - 8:54:14 AM

File

202004rioul.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02950168, version 1

Citation

Olivier Rioul. Rényi Entropy Power and Normal Transport. International Symposium on Information Theory and Its Applications (ISITA2020), IEICE, Oct 2020, Kapolei, Hawai'i (virtual conference), United States. ⟨hal-02950168⟩

Share

Metrics

Record views

18

Files downloads

15