Jensen-Shannon divergence is a symmetric measure of similarity between two probability distributions P and Q. It is defined as JS(P||Q) = 0.5·KL(P||M) + 0.5·KL(Q||M) where M = 0.5·(P+Q) is the midpoint distribution and KL denotes the Kullback-Leibler divergence. Unlike KL divergence, JS divergence is symmetric (JS(P||Q) = JS(Q||P)) and always finite for distributions with overlapping support. It takes values in [0, log(2)], with 0 indicating identical distributions and log(2) indicating maximum divergence. The square root of JS divergence satisfies the triangle inequality, making it a metric when square-rooted. It persists as a mathematical construct through its closed-form definition and is used in clustering, density estimation, and natural language processing. [formal: divergentia Jensen-Shannon | substrate: mind | horizon: hours | explicit: yes | epoch: 0.01]
Accepted ontology entry
jensen-shannon divergence
Jensen-Shannon divergence is a symmetric measure of similarity between two probability distributions P and Q. It is defined as JS(P||Q) = 0.5·KL(P||M) + 0.5·KL(Q||M) where M = 0.5·(P+Q) is the midpoint distribution and KL denotes the Kullb…
Definition
Why it is in scope
A symmetric, smoothed measure of the difference between two probability distributions, defined as the weighted average of the KL divergences from each distribution to their midpoint. It is human-made as a formal information-theoretic construct, persisted through its closed-form mathematical definition and used as a distance-like measure in statistics, machine learning, and natural language processing.
Names and aliases
- jensen-shannon divergenceen · CANONICAL
Relations from this entry
- relative-entropyDERIVED_FROM →
KL divergence existed first and fed into Jensen-Shannon divergence. Per Law 7 (which-came-first), KL was introduced by Kullback and Leibler in 1951, while Jensen-Shannon divergence in 1987 built upon it by adding symmetry and smoothing.
- cmsftujnv00f0qszgpolboiajDEPENDS_ON →
Jensen-Shannon divergence is an information-theoretic measure — it quantifies the similarity of two probability distributions using concepts (entropy, expected log) from information theory. Remove information theory and the measure has no mathematical foundation to operate. Removal test passes.
- f-divergenceINSTANCE_OF →
Jensen-Shannon divergence is an f-divergence with generating function f(t) = t·log(2t/(t+1)), a strictly convex function with f(1)=0. Every JS divergence is a specific f-divergence, and a competent speaker would classify it as 'a type of f-divergence'. f-divergence is the nearest kind between JS and the broader statistical-divergence.
Relations to this entry
No accepted relations in this direction.
Record identity
- Created
- Aug 5, 2026, 9:39 AM UTC
- Content hash
- f14074d2d03ea8a568a0e56a976e8c822fb166ae7937eec058f783575f782183