Documentation

EValues.LowerBound

Lower bound on e-Rényi and e-Chernoff divergences #

This file contains proofs of lower bounds on the e-Rényi and e-Chernoff divergences between sets of probability measures with bounded expectations.

Results #

theorem ProbabilityTheory.erenyiDiv_ge_of_separated {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {S T : Set (MeasureTheory.Measure 𝓧)} {f : 𝓧unitInterval} (hf : Measurable f) (hS : μS, MeasureTheory.IsProbabilityMeasure μ) (hT : μT, MeasureTheory.IsProbabilityMeasure μ) {δ : } (hδ_pos : 0 < δ) ( : δ 2⁻¹) (hSf : μS, (ω : 𝓧), (f ω) μ δ) (hTf : νT, 1 - δ (ω : 𝓧), (f ω) ν) :
ENNReal.ofReal (Real.log (1 / (4 * δ * (1 - δ)))) erenyiDiv 2⁻¹ S T
theorem ProbabilityTheory.echernoffDiv_ge_of_separated {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {S T : Set (MeasureTheory.Measure 𝓧)} {f : 𝓧unitInterval} (hf : Measurable f) (hS : μS, MeasureTheory.IsProbabilityMeasure μ) (hT : μT, MeasureTheory.IsProbabilityMeasure μ) {δ : } (hδ_pos : 0 < δ) ( : δ 2⁻¹) (hSf : μS, (ω : 𝓧), (f ω) μ δ) (hTf : νT, 1 - δ (ω : 𝓧), (f ω) ν) :
2⁻¹ * ENNReal.ofReal (Real.log (1 / (4 * δ * (1 - δ)))) echernoffDiv S T