Pointwise Partial Information Decomposition using the Specificity and Ambiguity Lattices

TL;DR

This paper introduces a novel approach to partial information decomposition by separately analyzing specificity and ambiguity, leading to more accurate measures of redundant information and new insights into multivariate information sharing.

Contribution

It proposes a new pointwise partial information decomposition framework based on specificity and ambiguity, overcoming limitations of previous measures and satisfying a chain rule.

Findings

The new decomposition provides clearer insights into information sharing.

It satisfies a chain rule over target variables.

The approach improves understanding of redundancy in information theory.

Abstract

What are the distinct ways in which a set of predictor variables can provide information about a target variable? When does a variable provide unique information, when do variables share redundant information, and when do variables combine synergistically to provide complementary information? The redundancy lattice from the partial information decomposition of Williams and Beer provided a promising glimpse at the answer to these questions. However, this structure was constructed using a much criticised measure of redundant information, and despite sustained research, no completely satisfactory replacement measure has been proposed. In this paper, we take a different approach, applying the axiomatic derivation of the redundancy lattice to a single realisation from a set of discrete variables. To overcome the difficulty associated with signed pointwise mutual information, we apply this decomposition separately to the unsigned entropic components of pointwise mutual information which we refer to as the specificity and ambiguity. This yields a separate redundancy lattice for each component. Then based upon an operational interpretation of redundancy, we define measures of redundant specificity and ambiguity enabling us to evaluate the partial information atoms in each lattice. These atoms can be recombined to yield the sought-after multivariate information decomposition. We apply this framework to canonical examples from the literature and discuss the results and the various properties of the decomposition. In particular, the pointwise decomposition using specificity and ambiguity satisfies a chain rule over target variables, which provides new insights into the so-called two-bit-copy example.