An information theoretic necessary condition for perfect reconstruction
Idris Delsol, Olivier Rioul, Julien B\'eguinot, Victor Rabiet, Antoine, Souloumiac

TL;DR
This paper introduces a new information theoretic necessary condition for perfect reconstruction of a discrete random variable from functions, based on Shannon's lattice theory and entropic metrics, with applications to various reconstruction problems.
Contribution
It provides a synthetic, detailed description of Shannon's lattice theory and introduces a geometric interpretation leading to a necessary condition for reconstruction.
Findings
A new geometric interpretation of Shannon's lattice theory.
A necessary (and sometimes sufficient) condition for perfect reconstruction.
Illustrations with five specific examples of reconstruction problems.
Abstract
A new information theoretic condition is presented for reconstructing a discrete random variable based on the knowledge of a set of discrete functions of . The reconstruction condition is derived from Shannon's 1953 lattice theory with two entropic metrics of Shannon and Rajski. Because such a theoretical material is relatively unknown and appears quite dispersed in different references, we first provide a synthetic description (with complete proofs) of its concepts, such as total, common and complementary informations. Definitions and properties of the two entropic metrics are also fully detailed and shown compatible with the lattice structure. A new geometric interpretation of such a lattice structure is then investigated that leads to a necessary (and sometimes sufficient) condition for reconstructing the discrete random variable given a set of…
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Retrieval and Classification Techniques · Computability, Logic, AI Algorithms · Rough Sets and Fuzzy Logic
