Concept
KL divergence
Kullback-Leibler (KL) divergence measures how far one probability distribution P strays from a reference distribution Q. Think of it like a distance between distributions, except it is not symmetric: KL(P||Q) generally does not equal KL(Q||P), and it is not a true…
The rest of “KL divergence” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→