Unique information via dependency constraints
From MaRDI portal
Abstract: The partial information decomposition (PID) is perhaps the leading proposal for resolving information shared between a set of sources and a target into redundant, synergistic, and unique constituents. Unfortunately, the PID framework has been hindered by a lack of a generally agreed-upon, multivariate method of quantifying the constituents. Here, we take a step toward rectifying this by developing a decomposition based on a new method that quantifies unique information. We first develop a broadly applicable method---the dependency decomposition---that delineates how statistical dependencies influence the structure of a joint distribution. The dependency decomposition then allows us to define a measure of the information about a target that can be uniquely attributed to a particular source as the least amount which the source-target statistical dependency can influence the information shared between the sources and the target. The result is the first measure that satisfies the core axioms of the PID framework while not satisfying the Blackwell relation, which depends on a particular interpretation of how the variables are related. This makes a key step forward to a practical PID.
Recommendations
- Common information and unique disjointness
- Properties of unique information
- Uniquest: Determining the Semantics of Complex Uniqueness Constraints
- scientific article; zbMATH DE number 3975376
- Uniqueness of information measure in the theory of evidence
- Constrained dependencies
- Uniqueness logic
- Chain Independence and Common Information
- Adding inclusion dependencies to an object-oriented data model with uniqueness constraints
Cites work
- A Mathematical Theory of Communication
- An overview of reconstructability analysis
- Causation entropy identifies indirect influences, dominance of neighbors and anticipatory couplings
- Elements of Information Theory
- scientific article; zbMATH DE number 2061729 (Why is no real title available?)
- Information geometry on hierarchy of probability distributions
- Information theory and network coding
- Papers on probability, statistics and statistical physics. Ed. by R. D. Rosenkrantz.
- Ross Ashby's information theory: a bit of history, some solutions to problems, and what we face today
- Shannon entropy and mutual information for multivariate skew-elliptical distributions
- The lattice theory of information
- Unconditionally secure key agreement and the intrinsic conditional information
Cited in
(8)- Properties of unique information
- Shannon’s information theory 70 years on: applications in classical and quantum physics
- Information decomposition based on cooperative game theory
- An operational information decomposition via synergistic disclosure
- Continuity and additivity properties of information decompositions
- Information theory for complex systems scientists: what, why, and how
- Simple physical systems as a reference for multivariate information dynamics
- Bits and pieces: understanding information decomposition from part-whole relationships and formal logic
This page was built for publication: Unique information via dependency constraints
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5235162)
