Stochastic expansion of the lower endpoint for the optimal value
ProvedGenEmpLik.Coverage.expansion_after_37_lowerAssume the hypotheses of Theorem 3: is nonempty and compact, the losses are measurable and satisfy Assumption B with , for some , satisfies Assumption A, are i.i.d. with law , and the population optimizer is unique with . Let and be the influence function of . Then
Here the infimum runs over probability weight vectors on the sample with , , and is the empirical variance with normalization . This is the lower-endpoint counterpart of the expansion displayed after (37). It follows from the same argument applied to , that is, Theorem 9 for the negated influence function together with Lemma 16. Combined with the central limit theorem, it gives .
Formalization note. is stated as: for every , the (outer) probability that the absolute value of the left-hand side exceeds tends to .
import Mathlib import Definitions.Def_GenEmpLik_Coverage_AssumptionA import Definitions.Def_GenEmpLik_Coverage_AssumptionB import Definitions.Def_GenEmpLik_Coverage_optimalValue import Definitions.Def_GenEmpLik_Coverage_empiricalOptimalValue import Definitions.Def_GenEmpLik_Coverage_divergenceBall import Definitions.Def_GenEmpLik_Coverage_confidenceSet import Definitions.Def_GenEmpLik_Coverage_influence import Definitions.Def_GenEmpLik_Coverage_remainder import Definitions.Def_GenEmpLik_Coverage_robustUpper import Definitions.Def_GenEmpLik_Coverage_uniqueOptimizer import Definitions.Def_VarianceRegularization_Expansion_empMean import Definitions.Def_VarianceRegularization_Expansion_empVar open MeasureTheory ProbabilityTheory Filter Topology
namespace GenEmpLik.Coverage
/-- The lower counterpart of the stochastic expansion in Appendix B.4 after (37), p. 37, for
T_opt, obtained by the symmetric argument on -T (Theorem 9 applied to the negated influence
function, together with Lemma 16). -/
theorem expansion_after_37_lower
{Ω Ξ : Type*} [MeasurableSpace Ω] [MeasurableSpace Ξ]
(μ : Measure Ω) [IsProbabilityMeasure μ]
(ξ : ℕ → Ω → Ξ) (d : ℕ)
(X : Set (EuclideanSpace ℝ (Fin d)))
(ℓ : EuclideanSpace ℝ (Fin d) → Ξ → ℝ)
(M : Ξ → ℝ) (f : ℝ → EReal) (ρ : ℝ)
(hρ : 0 ≤ ρ) (hA : AssumptionA f)
(hX : X.Nonempty) (hB : AssumptionB X ℓ M)
(hℓmeas : ∀ x, Measurable (ℓ x))
(hM2 : Integrable (fun z => M z ^ 2) (μ.map (ξ 0)))
(hℓ2 : ∃ x0 ∈ X, Integrable (fun z => ℓ x0 z ^ 2) (μ.map (ξ 0)))
(hξmeas : ∀ i, Measurable (ξ i))
(hξindep : iIndepFun ξ μ)
(hξident : ∀ i, IdentDistrib (ξ i) (ξ 0) μ μ)
(hunique : HasUniqueOptimizer X ℓ (μ.map (ξ 0)))
(hvar : 0 < variance (ℓ (uniqueOptimizer X ℓ (μ.map (ξ 0)) hunique))
(μ.map (ξ 0))) :
∀ δ : ℝ, 0 < δ →
Tendsto (fun n : ℕ => μ {ω |
δ < |Real.sqrt (n : ℝ) *
(sInf (empiricalOptimalValue X ℓ (fun i : Fin n => ξ i ω) '' divergenceBall f ρ n) -
optimalValue X ℓ (μ.map (ξ 0))) -
Real.sqrt (n : ℝ) *
VarianceRegularization.Expansion.empMean
(fun i : Fin n => influence ℓ
(uniqueOptimizer X ℓ (μ.map (ξ 0)) hunique)
(μ.map (ξ 0)) (ξ i ω)) +
Real.sqrt (ρ * VarianceRegularization.Expansion.empVar
(fun i : Fin n => influence ℓ
(uniqueOptimizer X ℓ (μ.map (ξ 0)) hunique)
(μ.map (ξ 0)) (ξ i ω)))|}) atTop (𝓝 0) := by sorry
end GenEmpLik.Coverage