← 研踪 PaperTrailarXiv:2601.03064 · v3
Similarity-Sensitive Entropy under Representation Change and Inference
首次提交 2026-01-06 22:46
版本更新 2026-11-13 03:47
雷达观测 2026-11-17 04:58
摘要
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.
作者备注:26 pages. v3: Revised abstract; generalized coarse graining proof; added further directions; revised theorem statements
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-13 03:47 · 最新观测版本
Similarity-Sensitive Entropy under Representation Change and Inference
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.
查看此版本解读 →查看此版本原文 ↗