no. 15 · Monday 16 November 2026
Similarity-Sensitive Entropy under Representation Change and Inference
Abstract
Similarity-sensitive entropy measures the uncertainty of a probability law relative to a similarity kernel that encodes the distinguishability of states. We develop the measure-theoretic treatment covering both finite similarity matrices and general probability spaces, and study how the law and similarity kernel transform under measurable maps, channels, and conditioning operations. This yields data-processing inequalities, so a reduction in entropy quantifies how much distinguishability is lost under representation change. We also define a conditional similarity-sensitive entropy theory, give a counterexample to a recent conjecture on concavity, and identify a practical one-dimensional Laplace kernel class where concavity holds.
- comments
- 26 pages. v3: Revised abstract; generalized coarse graining proof; added further directions; revised theorem statements
- fields
- Probability, Information Theory