Mathlib Map

Theorems · Theorem · information theory

InformationTheory.klDiv_compProd_eq_add

∀ {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} (μ ν : MeasureTheory.Measure 𝓧)
  (κ η : ProbabilityTheory.Kernel 𝓧 𝓨) [MeasureTheory.IsFiniteMeasure μ] [MeasureTheory.IsFiniteMeasure ν]
  [ProbabilityTheory.IsMarkovKernel κ] [ProbabilityTheory.IsMarkovKernel η],
  InformationTheory.klDiv (μ.compProd κ) (ν.compProd η) =
    InformationTheory.klDiv μ ν + InformationTheory.klDiv (μ.compProd κ) (μ.compProd η)

Chain rule for the Kullback-Leibler divergence, with conditional KL expressed using composition-products. This version holds without any assumption on the measurable spaces.

Defined in
Mathlib.InformationTheory.KullbackLeibler.ChainRule
Cited by
0 results in Mathlib
Foundations
Depth 273 from the axioms · uses propext, Classical.choice, Quot.sound
Assumes
MeasureTheory.IsFiniteMeasureMeasureTheory.IsFiniteMeasureProbabilityTheory.IsMarkovKernelProbabilityTheory.IsMarkovKernel

Around this declaration

Dashed lines are statement dependencies; solid lines are citations in proofs.

Cites34

Mathlib declarations this one mentions in its statement or cites explicitly in its proof. Plumbing is filtered out.

Cited by0

Results whose statement or proof uses this declaration.

Nothing cites this yet.