BanditAlgorithm.gaussian_relative_entropy_formula
Provedgaussianinformation-theory
(Gaussian KL formula) For means and common variance (Mathlib's gaussianReal takes the VARIANCE , not the standard deviation):
stated with InformationTheory.klDiv valued in . The hypothesis is required: Mathlib defines gaussianReal μ 0 = dirac μ, so at the true KL is if and otherwise, while the formula's right-hand side would be the junk value ofReal(x/0) = 0.
Preamble
import Mathlib.InformationTheory.KullbackLeibler.Basic import Mathlib.Probability.Distributions.Gaussian.Real open MeasureTheory ProbabilityTheory InformationTheory NNReal
Formal statement
theorem BanditAlgorithm.gaussian_relative_entropy_formula (μ₁ μ₂ : ℝ) {v : ℝ≥0} (hv : v ≠ 0) :
klDiv (gaussianReal μ₁ v) (gaussianReal μ₂ v) =
ENNReal.ofReal ((μ₁ - μ₂) ^ 2 / (2 * (v : ℝ))) := by
sorry
Source
L&S Ch 14.2 (specialization of Theorem 14.1), p.190