The Information Bottleneck Method: Fundamental Idea and Algorithmic Implementations

Author: D. Wübben

The quantized representation of signals is a general task of data processing. For lossy data compression the celebrated Rate-Distortion theory provides the compression rate in order to quantize a signal without exceeding a given distortion measure. Recently, with the Information Bottleneck method an alternative approach has been emerged in the field of machine learning and has been successfully applied for data processing. The fundamental idea is to include the original source into the problem setup when quantizing an observation variable and to use strictly information theoretic measures to design the quantizer. This paper introduces this framework and discusses algorithmic implementations for the quantizer design.

Document type: Conference Paper
Publication: ISBN 978-90-74249-29-4, Boppard, Germany, 21. - 23. June 2017
Conference: 10th Asia-Europe Workshop on Concepts in Information Theory (AEW 2017)
AEW_2017_IBM_Wuebben.pdf200 KB
Last change on 27.06.2017 by D. Wübben
AIT ieee GOC tzi ith Fachbereich 1
© Department of Communications Engineering - University of BremenImprint / Contact