Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Corollary 1 — robust optimal values and solution sets over f-divergence balls are consistent

Proved
GenEmpLik.Consistency.corollary_1

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

consistencydistributionally-robust-optimizationp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1stochastic-optimization

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​ and let P^n\widehat P_nPn​ be the empirical distribution of the first nnn. Let X⊂Rd\mathcal X\subset\mathbb R^dX⊂Rd be nonempty and compact, let ℓ:Rd×Ξ→R\ell:\mathbb R^d\times\Xi\to\mathbb Rℓ:Rd×Ξ→R be lower semicontinuous on X×Ξ\mathcal X\times\XiX×Ξ, with ℓ(x;⋅)\ell(x;\cdot)ℓ(x;⋅) measurable for every x∈Xx\in\mathcal Xx∈X and ℓ(⋅;ξ)\ell(\cdot;\xi)ℓ(⋅;ξ) continuous on X\mathcal XX for every ξ\xiξ. Let fff satisfy Assumption A, ρ≥0\rho\ge0ρ≥0, and let Assumption E hold. Define the robust and population objectives

F^n(x)=sup⁡P≪P^n{EP[ℓ(x;ξ)]:Df(P∥P^n)≤ρn},F(x)=EP0[ℓ(x;ξ)],\widehat F_n(x)=\sup_{P\ll\widehat P_n}\Big\{E_P[\ell(x;\xi)] : D_f(P\|\widehat P_n)\le\frac{\rho}{n}\Big\},\qquad F(x)=E_{P_0}[\ell(x;\xi)],Fn​(x)=P≪Pn​sup​{EP​[ℓ(x;ξ)]:Df​(P∥Pn​)≤nρ​},F(x)=EP0​​[ℓ(x;ξ)],

and the solution sets SP^n⋆=argmin⁡x∈XF^n(x)S^\star_{\widehat P_n}=\operatorname{argmin}_{x\in\mathcal X}\widehat F_n(x)SPn​⋆​=argminx∈X​Fn​(x) and SP0⋆=argmin⁡x∈XF(x)S^\star_{P_0}=\operatorname{argmin}_{x\in\mathcal X}F(x)SP0​⋆​=argminx∈X​F(x). Then, in outer probability,

inf⁡x∈XF^n(x)−inf⁡x∈XF(x) → P∗  0andd⊂(SP^n⋆,SP0⋆) → P∗  0.\inf_{x\in\mathcal X}\widehat F_n(x)-\inf_{x\in\mathcal X}F(x)\ \xrightarrow{\ P^*\ }\ 0 \qquad\text{and}\qquad d_\subset\big(S^\star_{\widehat P_n},S^\star_{P_0}\big)\ \xrightarrow{\ P^*\ }\ 0 .x∈Xinf​Fn​(x)−x∈Xinf​F(x)  P∗ ​ 0andd⊂​(SPn​⋆​,SP0​⋆​)  P∗ ​ 0.

So the optimal value of the distributionally robust problem is a consistent estimate of the population optimal value, and its minimisers eventually lie arbitrarily close to the population minimisers: robustness costs nothing in consistency under these conditions.

Formalization Note Convergence in outer probability is stated as: for every δ>0\delta>0δ>0, μ∗{ω:δ<∣⋅∣}→0\mu^*\{\omega : \delta<|\cdot|\}\to0μ∗{ω:δ<∣⋅∣}→0, where μ s\mu\,sμs for an arbitrary set sss is Mathlib's outer measure (no measurability assumed). d⊂d_\subsetd⊂​ takes values in [0,∞][0,\infty][0,∞] and the second event is {δ<d⊂}\{\delta<d_\subset\}{δ<d⊂​}. Samples are 0-based, P0P_0P0​ is the law of ξ0\xi_0ξ0​, and F^n(x)\widehat F_n(x)Fn​(x) is robustMean f ρ (ℓ(x;ξ_0),…,ℓ(x;ξ_{n-1})). Nonemptiness of X\mathcal XX is the paper's standing assumption (p. 1); nonemptiness of the solution sets is not assumed.

Preamble
import Mathlib
import Definitions.Def_GenEmpLik_Coverage_AssumptionA
import Definitions.Def_GenEmpLik_Consistency_AssumptionE
import Definitions.Def_GenEmpLik_Expansion_robustMean
import Definitions.Def_GenEmpLik_Consistency_argminSet
import Definitions.Def_GenEmpLik_Consistency_inclDist

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

/-- Corollary 1 (arXiv:1610.03425v3, p. 17). Let `ξ₀, ξ₁, …` be i.i.d. with law `P₀`, let `f`
satisfy Assumption A, `ρ ≥ 0`, let `X ⊂ ℝ^d` be nonempty and compact, and let `Ξ` be a
separable metric space. Let `ℓ` be lower semicontinuous on `X × Ξ`, `ℓ(·; ξ)` continuous on
`X` for every `ξ`, `ℓ(x; ·)` measurable for `x ∈ X`, and let Assumption E hold. With
`F̂_n(x) = sup { E_P[ℓ(x; ξ)] : P ≪ P̂_n, D_f(P ‖ P̂_n) ≤ ρ/n }` and `F(x) = E_{P₀}[ℓ(x; ξ)]`,
`inf_X F̂_n − inf_X F → 0` and `d_⊂(argmin_X F̂_n, argmin_X F) → 0` in outer probability. -/
theorem corollary_1 {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))) (hX : IsCompact X) (hXne : X.Nonempty)
    (ℓ : EuclideanSpace ℝ (Fin d) → Ξ → ℝ) (hℓm : ∀ x ∈ X, Measurable (ℓ x))
    (hℓlsc : LowerSemicontinuous (fun xs : X × Ξ => ℓ xs.1 xs.2))
    (hcont : ∀ s, ContinuousOn (fun x => ℓ x s) X)
    (hE : AssumptionE (μ.map (ξ 0)) X ℓ) :
    (∀ δ : ℝ, 0 < δ → Tendsto (fun n : ℕ => μ {ω |
        δ < |(⨅ x : X, GenEmpLik.Expansion.robustMean f ρ (fun i : Fin n => ℓ x (ξ i ω)))
          - ⨅ x : X, ∫ s, ℓ x s ∂(μ.map (ξ 0))|}) atTop (𝓝 0)) ∧
    (∀ δ : ℝ, 0 < δ → Tendsto (fun n : ℕ => μ {ω |
        ENNReal.ofReal δ < inclDist
          (argminSet X (fun x => GenEmpLik.Expansion.robustMean f ρ (fun i : Fin n => ℓ x (ξ i ω))))
          (argminSet X (fun x => ∫ 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. 17, Corollary 1 (with (23), p. 16, and (6), p. 5)
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