Collaborative Information Bottleneck

DOI10.1109/TIT.2018.2883295zbMATH Open1427.94066arXiv1604.01433OpenAlexW2770297754WikidataQ128875162 ScholiaQ128875162MaRDI QIDQ4615342FDOQ4615342

Pablo Piantanida, Matías Vera, Leonardo Rey Vega

Publication date: 28 January 2019

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: This paper investigates a multi-terminal source coding problem under a logarithmic loss fidelity which does not necessarily lead to an additive distortion measure. The problem is motivated by an extension of the Information Bottleneck method to a multi-source scenario where several encoders have to build cooperatively rate-limited descriptions of their sources in order to maximize information with respect to other unobserved (hidden) sources. More precisely, we study fundamental information-theoretic limits of the so-called: (i) Two-way Collaborative Information Bottleneck (TW-CIB) and (ii) the Collaborative Distributed Information Bottleneck (CDIB) problems. The TW-CIB problem consists of two distant encoders that separately observe marginal (dependent) components

X_{1}

and

X_{2}

and can cooperate through multiple exchanges of limited information with the aim of extracting information about hidden variables

(Y_{1}, Y_{2})

, which can be arbitrarily dependent on

(X_{1}, X_{2})

. On the other hand, in CDIB there are two cooperating encoders which separately observe

X_{1}

and

X_{2}

and a third node which can listen to the exchanges between the two encoders in order to obtain information about a hidden variable

Y

. The relevance (figure-of-merit) is measured in terms of a normalized (per-sample) multi-letter mutual information metric (log-loss fidelity) and an interesting tradeoff arises by constraining the complexity of descriptions, measured in terms of the rates needed for the exchanges between the encoders and decoders involved. Inner and outer bounds to the complexity-relevance region of these problems are derived from which optimality is characterized for several cases of interest. Our resulting theoretical complexity-relevance regions are finally evaluated for binary symmetric and Gaussian statistical models.

Full work available at URL: https://arxiv.org/abs/1604.01433

Mathematics Subject Classification ID

Measures of information, entropy (94A17) Source coding (94A29)

Cited In (3)

This page was built for publication: Collaborative Information Bottleneck

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4615342)