Skip to Main content Skip to Navigation
Conference papers

Distributed Information Bottleneck Method for Discrete and Gaussian Sources

Abstract : We study the problem of distributed information bottleneck, in which multiple encoders separately compress their observations in a manner such that, collectively, the compressed signals preserve as much information as possible about another signal. The model generalizes Tishby's centralized information bottleneck method to the setting of multiple distributed encoders. We establish single-letter characterizations of the information-rate region of this problem for both i) a class of discrete memoryless sources and ii) memoryless vector Gaussian sources. Furthermore, assuming a sum constraint on rate or complexity, for both models we develop Blahut-Arimoto type iterative algorithms that allow to compute optimal information-rate trade-offs, by iterating over a set of self-consistent equations.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01806552
Contributor : Abdellatif Zaidi <>
Submitted on : Sunday, June 3, 2018 - 4:14:06 PM
Last modification on : Wednesday, February 26, 2020 - 7:06:07 PM

Links full text

Identifiers

  • HAL Id : hal-01806552, version 1
  • ARXIV : 1709.09082

Citation

Inaki Estella Aguerri, Abdellatif Zaidi. Distributed Information Bottleneck Method for Discrete and Gaussian Sources. International Zurich Seminar on Information and Communication, Feb 2018, Zurich, Switzerland. ⟨hal-01806552⟩

Share

Metrics

Record views

64