English

Extracting Unique Information Through Markov Relations

Information Theory 2023-07-21 v1 math.IT

Abstract

We propose two new measures for extracting the unique information in XX and not YY about a message MM, when X,YX, Y and MM are joint random variables with a given joint distribution. We take a Markov based approach, motivated by questions in fair machine learning, and inspired by similar Markov-based optimization problems that have been used in the Information Bottleneck and Common Information frameworks. We obtain a complete characterization of our definitions in the Gaussian case (namely, when X,YX, Y and MM are jointly Gaussian), under the assumption of Gaussian optimality. We also examine the consistency of our definitions with the partial information decomposition (PID) framework, and show that these Markov based definitions achieve non-negativity, but not symmetry, within the PID framework.

Keywords

Cite

@article{arxiv.2210.14789,
  title  = {Extracting Unique Information Through Markov Relations},
  author = {Keerthana Gurushankar and Praveen Venkatesh and Pulkit Grover},
  journal= {arXiv preprint arXiv:2210.14789},
  year   = {2023}
}
R2 v1 2026-06-28T04:34:27.606Z