A KL-centroid optimization problem leads to a closed-form solution with Lambert W

FrnkNlsn · x · 2026-08-04

The post describes a variational optimization problem: finding a distribution r that minimizes DKL[p:r] + DKL[r:q]. The solution is expressed with the Lambert W function, and the unique normalizing constant λ is what makes r a valid probability distribution.

It also notes that this appears in Jeffreys centroids and symmetrized Bregman centroids.

Original post →

More from Research

Research channel →