A Class of Nonbinary Symmetric Information Bottleneck Problems

10/03/2021
βˆ™
by   Michael Dikshtein, et al.
βˆ™
0
βˆ™

We study two dual settings of information processing. Let 𝖸→𝖷→𝖢 be a Markov chain with fixed joint probability mass function 𝖯_𝖷𝖸 and a mutual information constraint on the pair (𝖢,𝖷). For the first problem, known as Information Bottleneck, we aim to maximize the mutual information between the random variables 𝖸 and 𝖢, while for the second problem, termed as Privacy Funnel, our goal is to minimize it. In particular, we analyze the scenario for which 𝖷 is the input, and 𝖸 is the output of modulo-additive noise channel. We provide analytical characterization of the optimal information rates and the achieving distributions.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset