Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 7 — the f-divergence robust objective converges uniformly to E_{P₀}[ℓ(x; ξ)] almost surely

Proved
GenEmpLik.Consistency.theorem_7

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

consistencydistributionally-robust-optimizationp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1uniform-law-of-large-numbers

Let ξ1,ξ2,…\xi_1,\xi_2,\dotsξ1​,ξ2​,… be i.i.d. random elements of a separable metric space Ξ\XiΞ with law P0P_0P0​, let P^n\widehat P_nPn​ be the empirical distribution of the first nnn, and let X⊂Rd\mathcal X\subset\mathbb R^dX⊂Rd be nonempty and closed. Let ℓ\ellℓ be lower semicontinuous on X×Ξ\mathcal X\times\XiX×Ξ and ℓ(x;⋅)\ell(x;\cdot)ℓ(x;⋅) measurable for each x∈Xx\in\mathcal Xx∈X. Let fff satisfy Assumption A, let ρ≥0\rho\ge0ρ≥0, let Assumption E hold, and assume the class {ℓ(x;⋅):x∈X}\{\ell(x;\cdot):x\in\mathcal X\}{ℓ(x;⋅):x∈X} is Glivenko–Cantelli. Then

sup⁡x∈X sup⁡P≪P^n{∣EP[ℓ(x;ξ)]−EP0[ℓ(x;ξ)]∣:Df(P∥P^n)≤ρn} → a.s.∗  0.\sup_{x\in\mathcal X}\ \sup_{P\ll\widehat P_n}\Big\{\big|E_P[\ell(x;\xi)]-E_{P_0}[\ell(x;\xi)]\big| : D_f\big(P\|\widehat P_n\big)\le\frac{\rho}{n}\Big\}\ \xrightarrow{\ \text{a.s.}^*\ }\ 0 .x∈Xsup​ P≪Pn​sup​{​EP​[ℓ(x;ξ)]−EP0​​[ℓ(x;ξ)]​:Df​(P∥Pn​)≤nρ​}  a.s.∗ ​ 0.

Thus the robust objective, and every reweighting in the ρ/n\rho/nρ/n divergence ball, converges to the population risk uniformly over the decision set, under only slightly more than the first-moment condition needed for sample average approximation.

Formalization Note A distribution P≪P^nP\ll\widehat P_nP≪Pn​ is a weight vector ppp on the first nnn samples ξ0,…,ξn−1\xi_0,\dots,\xi_{n-1}ξ0​,…,ξn−1​ (0-based), feasible when p∈p\inp∈ probUncertaintySet f (1/n,…,1/n) (ρ/n). Both suprema are taken in [0,∞][0,\infty][0,∞]. Almost-sure convergence is ∀ᵐ (outer measure of the exceptional set is zero), the same reading as in the Glivenko–Cantelli hypothesis. i.i.d. means measurable, mutually independent (iIndepFun) and identically distributed with ξ0\xi_0ξ0​; P0P_0P0​ is the law of ξ0\xi_0ξ0​.

Preamble
import Mathlib
import Definitions.Def_PhiDivRobust_Counterpart_uncertaintySet
import Definitions.Def_GenEmpLik_Coverage_AssumptionA
import Definitions.Def_GenEmpLik_Consistency_AssumptionE
import Definitions.Def_GenEmpLik_Consistency_IsGlivenkoCantelli

open MeasureTheory ProbabilityTheory Filter Topology
open scoped ENNReal
Formal statement
namespace GenEmpLik.Consistency

/-- Theorem 7 (arXiv:1610.03425v3, p. 16; proof App. E.1, pp. 46–47). Let `ξ₀, ξ₁, …` be
i.i.d. with law `P₀` on a separable metric space, let `f` satisfy Assumption A, `ρ ≥ 0`,
and let `X` be nonempty and closed. Let the lower semicontinuous loss `ℓ` satisfy Assumption E
on `X`, with measurable `ℓ(x; ·)` for `x ∈ X`, and let `{ℓ(x; ·) : x ∈ X}` be
Glivenko–Cantelli. Then, almost surely,
`sup_{x ∈ X} sup { |E_P[ℓ(x; ξ)] − E_{P₀}[ℓ(x; ξ)]| : P ≪ P̂_n, D_f(P ‖ P̂_n) ≤ ρ/n } → 0`,
with `P ≪ P̂_n` the weight vectors `p` on the first `n` samples and the suprema in `[0, ∞]`. -/
theorem theorem_7 {Ω Ξ : Type*} [MeasurableSpace Ω] [MeasurableSpace Ξ] [MetricSpace Ξ]
    [SecondCountableTopology Ξ]
    {μ : Measure Ω} [IsProbabilityMeasure μ] {d : ℕ}
    (f : ℝ → EReal) (hf : GenEmpLik.Coverage.AssumptionA f) (ρ : ℝ) (hρ : 0 ≤ ρ)
    (ξ : ℕ → Ω → Ξ) (hξm : ∀ i, Measurable (ξ i)) (hξind : iIndepFun ξ μ)
    (hξid : ∀ i, IdentDistrib (ξ i) (ξ 0) μ μ)
    (X : Set (EuclideanSpace ℝ (Fin d))) (hXne : X.Nonempty) (hXclosed : IsClosed X)
    (ℓ : EuclideanSpace ℝ (Fin d) → Ξ → ℝ)
    (hℓlsc : LowerSemicontinuous (fun xs : X × Ξ => ℓ xs.1 xs.2))
    (hℓm : ∀ x ∈ X, Measurable (ℓ x))
    (hE : AssumptionE (μ.map (ξ 0)) X ℓ)
    (hGC : IsGlivenkoCantelli μ ξ ((fun x => ℓ x) '' X)) :
    ∀ᵐ ω ∂μ, Tendsto (fun n : ℕ => ⨆ x ∈ X,
        ⨆ p ∈ PhiDivRobust.Counterpart.probUncertaintySet f (fun _ : Fin n => (1 : ℝ) / n)
          (ρ / n),
        ENNReal.ofReal |∑ i, p i * ℓ x (ξ i ω) - ∫ s, ℓ x s ∂(μ.map (ξ 0))|)
      atTop (𝓝 0) := by sorry

end GenEmpLik.Consistency
Source
Duchi, Glynn & Namkoong, Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach, arXiv:1610.03425v3, p. 16, Theorem 7 (proof App. E.1, pp. 46–47)
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me