TL;DR
This paper introduces a new perspective on partial information decomposition (PID) by deriving it from elementary parthood relationships and linking it to formal logic, offering a unified understanding of information atoms.
Contribution
It demonstrates that PID can be derived from parthood considerations and establishes isomorphisms between PID, logical statements, and lattice structures, providing new insights into its foundations.
Findings
PID can be derived from elementary parthood relationships.
Logical and lattice structures are isomorphic to PID.
The parthood perspective helps address questions of uniqueness in PID.
Abstract
Partial information decomposition (PID) seeks to decompose the multivariate mutual information that a set of source variables contains about a target variable into basic pieces, the so called "atoms of information". Each atom describes a distinct way in which the sources may contain information about the target. In this paper we show, first, that the entire theory of partial information decomposition can be derived from considerations of elementary parthood relationships between information contributions. This way of approaching the problem has the advantage of directly characterizing the atoms of information, instead of taking an indirect approach via the concept of redundancy. Secondly, we describe several intriguing links between PID and formal logic. In particular, we show how to define a measure of PID based on the information provided by certain statements about source…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
