On Information Bottleneck for Gaussian Processes

Michael Dikshtein, Nir Weinberger, Shlomo Shamai Shitz

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


The information bottleneck (IB) problem of jointly stationary Gaussian sources is considered. A water-filling solution for the IB rate is given in terms of its SNR spectrum and whose rate is attained via frequency domain test-channel realization. A time-domain realization of the IB rate, based on linear prediction, is also proposed, which lends itself to an efficient implementation of the corresponding remote source-coding problem. A compound version of the problem is addressed, in which the joint distribution of the source is not precisely specified but rather in terms of a lower bound on the guaranteed mutual information. It is proved that a white SNR spectrum is optimal for this setting.

Original languageEnglish
Title of host publication2022 IEEE Information Theory Workshop, ITW 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781665483414
StatePublished - 2022
Externally publishedYes
Event2022 IEEE Information Theory Workshop, ITW 2022 - Mumbai, India
Duration: 1 Nov 20229 Nov 2022

Publication series

Name2022 IEEE Information Theory Workshop, ITW 2022


Conference2022 IEEE Information Theory Workshop, ITW 2022


Dive into the research topics of 'On Information Bottleneck for Gaussian Processes'. Together they form a unique fingerprint.

Cite this