The Multi-layer Information Bottleneck Problem
File(s)
Accepted version
Author(s)
Yang, Qianqian
Piantanidat, Pablo
Gunduz, Deniz
Type
Conference Paper
Abstract
The muti-layer information bottleneck (IB) problem, where information is propagated (or successively refined) from layer to layer, is considered. Based on information forwarded by the preceding layer, each stage of the network is required to preserve a certain level of relevance with regards to a specific hidden variable, quantified by the mutual information. The hidden variables and the source can be arbitrarily correlated. The optimal trade-off between rates of relevance and compression (or complexity) is obtained through a singleletter characterization, referred to as the rate-relevance region. Conditions of successive refinabilty are given. Binary source with BSC hidden variables and binary source with BSC/BEC mixed hidden variables are both proved to be successively refinable. We further extend our result to Guassian models. A counterexample of successive refinability is also provided.
Date Issued
2018-02-01
Date Acceptance
2017-11-06
Citation
2017 IEEE INFORMATION THEORY WORKSHOP (ITW), 2018, pp.404-408
ISSN
2475-420X
Publisher
IEEE
Start Page
404
End Page
408
Journal / Book Title
2017 IEEE INFORMATION THEORY WORKSHOP (ITW)
Copyright Statement
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor
Commission of the European Communities
Identifier
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000426901500082&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
Grant Number
677854
Source
2017 IEEE Information Theory Workshop (ITW)
Subjects
Science & Technology
Technology
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Computer Science
Engineering
Publication Status
Published
Start Date
2017-11-06
Finish Date
2017-11-10
Coverage Spatial
Kaohsiung, TAIWAN
Date Publish Online
2018-02-01