Documentation

EValues.Divergence

E-variable divergences #

We define analogues of the Rényi and Chernoff divergences for e-variables that share the same properties as the classical divergences. In particular, they satisfy a data processing inequality.

Main definitions #

Main statements #

noncomputable def ProbabilityTheory.erenyiDiv {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} (α : ENNReal) (S T : Set (MeasureTheory.Measure 𝓧)) :

The e-Rényi divergence between two sets of measures.

Note that the two integrals are non-negative, so the application of EReal.toENNReal does not truncate.

Equations
  • One or more equations did not get rendered due to their size.
Instances For
    theorem ProbabilityTheory.erenyiDiv_empty_left {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {α : ENNReal} {T : Set (MeasureTheory.Measure 𝓧)} ( : α 0) :
    theorem ProbabilityTheory.erenyiDiv_empty_right {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {α : ENNReal} {S : Set (MeasureTheory.Measure 𝓧)} ( : α < 1) :
    @[simp]
    theorem ProbabilityTheory.erenyiDiv_empty {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {α : ENNReal} :
    noncomputable def ProbabilityTheory.echernoffDiv {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} (S T : Set (MeasureTheory.Measure 𝓧)) :

    The e-Chernoff divergence between two sets of measures.

    Equations
    • One or more equations did not get rendered due to their size.
    Instances For
      theorem ProbabilityTheory.erenyiDiv_anti {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {α : ENNReal} {S₁ S₂ T₁ T₂ : Set (MeasureTheory.Measure 𝓧)} (hS : S₁ S₂) (hT : T₁ T₂) :
      erenyiDiv α S₂ T₂ erenyiDiv α S₁ T₁
      theorem ProbabilityTheory.echernoffDiv_anti {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {S₁ S₂ T₁ T₂ : Set (MeasureTheory.Measure 𝓧)} (hS : S₁ S₂) (hT : T₁ T₂) :
      echernoffDiv S₂ T₂ echernoffDiv S₁ T₁
      theorem ProbabilityTheory.erenyiDiv_comp_le {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} {S T : Set (MeasureTheory.Measure 𝓧)} {α : ENNReal} (κ : Kernel 𝓧 𝓨) [IsMarkovKernel κ] :
      erenyiDiv α {x : MeasureTheory.Measure 𝓨 | μS, μ.bind κ = x} {x : MeasureTheory.Measure 𝓨 | μT, μ.bind κ = x} erenyiDiv α S T

      Data processing inequality for the e-Rényi divergence with a Markov kernel.

      theorem ProbabilityTheory.erenyiDiv_map_le {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} {S T : Set (MeasureTheory.Measure 𝓧)} {α : ENNReal} {f : 𝓧𝓨} (hf : Measurable f) :

      Data processing inequality for the e-Rényi divergence with a measurable function.

      theorem ProbabilityTheory.echernoffDiv_comp_le {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} {S T : Set (MeasureTheory.Measure 𝓧)} (κ : Kernel 𝓧 𝓨) [IsMarkovKernel κ] :
      echernoffDiv {x : MeasureTheory.Measure 𝓨 | μS, μ.bind κ = x} {x : MeasureTheory.Measure 𝓨 | μT, μ.bind κ = x} echernoffDiv S T

      Data processing inequality for the e-Chernoff divergence with a Markov kernel.

      theorem ProbabilityTheory.echernoffDiv_map_le {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} {S T : Set (MeasureTheory.Measure 𝓧)} {f : 𝓧𝓨} (hf : Measurable f) :

      Data processing inequality for the e-Chernoff divergence with a measurable function.

      theorem ProbabilityTheory.erenyiDiv_add_eq_sInf {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} {α : ENNReal} (S₁ S₂ : Set (MeasureTheory.Measure 𝓧)) (T₁ T₂ : Set (MeasureTheory.Measure 𝓨)) :
      theorem ProbabilityTheory.erenyiDiv_prod_le {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} {α : ENNReal} {S₁ S₂ : Set (MeasureTheory.Measure 𝓧)} {T₁ T₂ : Set (MeasureTheory.Measure 𝓨)} (hS₁ : μS₁, MeasureTheory.IsFiniteMeasure μ) (hS₂ : μS₂, MeasureTheory.IsFiniteMeasure μ) (hT₁ : μT₁, MeasureTheory.IsFiniteMeasure μ) (hT₂ : μT₂, MeasureTheory.IsFiniteMeasure μ) :
      theorem ProbabilityTheory.erenyiDiv_prod {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} {α : ENNReal} {S₁ S₂ : Set (MeasureTheory.Measure 𝓧)} {T₁ T₂ : Set (MeasureTheory.Measure 𝓨)} (hS₁ : μS₁, MeasureTheory.IsFiniteMeasure μ) (hS₂ : μS₂, MeasureTheory.IsFiniteMeasure μ) (hT₁ : μT₁, MeasureTheory.IsFiniteMeasure μ) (hT₂ : μT₂, MeasureTheory.IsFiniteMeasure μ) :
      theorem ProbabilityTheory.echernoffDiv_prod_le {𝓧 : Type u_1} {𝓨 : Type u_2} {m𝓧 : MeasurableSpace 𝓧} {m𝓨 : MeasurableSpace 𝓨} {S₁ S₂ : Set (MeasureTheory.Measure 𝓧)} {T₁ T₂ : Set (MeasureTheory.Measure 𝓨)} (hS₁ : μS₁, MeasureTheory.IsFiniteMeasure μ) (hS₂ : μS₂, MeasureTheory.IsFiniteMeasure μ) (hT₁ : μT₁, MeasureTheory.IsFiniteMeasure μ) (hT₂ : μT₂, MeasureTheory.IsFiniteMeasure μ) :
      theorem ProbabilityTheory.erenyiDiv_of_involutive_aux {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {S T : Set (MeasureTheory.Measure 𝓧)} {φ : 𝓧𝓧} ( : Measurable φ) (hφ_inv : φ φ = id) (hφST : {x : MeasureTheory.Measure 𝓧 | μS, MeasureTheory.Measure.map φ μ = x} = T) :
      theorem ProbabilityTheory.erenyiDiv_of_involutive {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {S T : Set (MeasureTheory.Measure 𝓧)} {φ : 𝓧𝓧} ( : Measurable φ) (hφ_inv : φ φ = id) (hφST : {x : MeasureTheory.Measure 𝓧 | μS, MeasureTheory.Measure.map φ μ = x} = T) :
      theorem ProbabilityTheory.echernoffDiv_of_involutive_aux {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {S T : Set (MeasureTheory.Measure 𝓧)} {φ : 𝓧𝓧} ( : Measurable φ) (hφ_inv : φ φ = id) (hφST : {x : MeasureTheory.Measure 𝓧 | μS, MeasureTheory.Measure.map φ μ = x} = T) :
      theorem ProbabilityTheory.echernoffDiv_of_involutive {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {S T : Set (MeasureTheory.Measure 𝓧)} {φ : 𝓧𝓧} ( : Measurable φ) (hφ_inv : φ φ = id) (hφST : {x : MeasureTheory.Measure 𝓧 | μS, MeasureTheory.Measure.map φ μ = x} = T) :
      theorem ProbabilityTheory.erenyiDiv_eq_two_mul_echernoffDiv_of_involutive {𝓧 : Type u_1} {m𝓧 : MeasurableSpace 𝓧} {S T : Set (MeasureTheory.Measure 𝓧)} {φ : 𝓧𝓧} ( : Measurable φ) (hφ_inv : φ φ = id) (hφST : {x : MeasureTheory.Measure 𝓧 | μS, MeasureTheory.Measure.map φ μ = x} = T) :