Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 4.2, p. 13 — the case ε = 0: (10) is the sample average and (12b) tends to it as λ → ∞

Proved
WassDDRO.Reduction.worstCase_eq_sampleAverage_of_zero

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

distributionally-robust-optimizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1sample-average-approximationwasserstein

Let EEE, Ξ\XiΞ, ℓ=max⁡k≤Kℓk\ell=\max_{k\le K}\ell_kℓ=maxk≤K​ℓk​ and samples ξ^1,…,ξ^N∈Ξ\hat\xi_1,\dots,\hat\xi_N\in\Xiξ^​1​,…,ξ^​N​∈Ξ be as in Theorem 4.2 (K,N≥1K,N\ge1K,N≥1, each ℓk\ell_kℓk​ measurable), and suppose Assumption 4.1 holds. Then:

  1. with radius ε=0\varepsilon=0ε=0, the worst-case expectation (10) equals the sample average,
sup⁡Q∈B0(P^N)EQ[ℓ(ξ)]=1N∑i=1Nℓ(ξ^i);\sup_{\mathbb Q\in\mathbb B_0(\widehat{\mathbb P}_N)}\mathbb E^{\mathbb Q}[\ell(\xi)]=\frac1N\sum_{i=1}^N\ell(\hat\xi_i);Q∈B0​(PN​)sup​EQ[ℓ(ξ)]=N1​i=1∑N​ℓ(ξ^​i​);
  1. the objective of (12b) at ε=0\varepsilon=0ε=0 converges to the sample average as λ→∞\lambda\to\inftyλ→∞:
lim⁡λ→∞1N∑i=1Nsup⁡ξ∈Ξ(ℓ(ξ)−λ∥ξ−ξ^i∥)=1N∑i=1Nℓ(ξ^i);\lim_{\lambda\to\infty}\frac1N\sum_{i=1}^N\sup_{\xi\in\Xi}\big(\ell(\xi)-\lambda\|\xi-\hat\xi_i\|\big)=\frac1N\sum_{i=1}^N\ell(\hat\xi_i);λ→∞lim​N1​i=1∑N​ξ∈Ξsup​(ℓ(ξ)−λ∥ξ−ξ^​i​∥)=N1​i=1∑N​ℓ(ξ^​i​);
  1. consequently (12a) holds with equality also at ε=0\varepsilon=0ε=0: (10) with ε=0\varepsilon=0ε=0 equals the optimal value of (12c) with ε=0\varepsilon=0ε=0.

Together with the case ε>0\varepsilon>0ε>0 this shows that (10) equals (12c) for all ε≥0\varepsilon\ge0ε≥0.

Formalization Note The sums are taken in EReal. Under Assumption 4.1 no ℓk\ell_kℓk​ takes the value +∞+\infty+∞, so each ℓ(ξ^i)<+∞\ell(\hat\xi_i)<+\inftyℓ(ξ^​i​)<+∞, and for λ\lambdaλ large enough each inner supremum is <+∞<+\infty<+∞; the sums therefore never meet (+∞)+(−∞)(+\infty)+(-\infty)(+∞)+(−∞) where it matters, and a sample with ℓ(ξ^i)=−∞\ell(\hat\xi_i)=-\inftyℓ(ξ^​i​)=−∞ makes the average −∞-\infty−∞, as in the paper. The limit is in the order topology of R‾\overline{\mathbb R}R.

Preamble
import Mathlib
import Definitions.Def_WassDDRO_Reduction_Setting

open MeasureTheory Filter Topology
Formal statement
namespace WassDDRO.Reduction

/-- Proof of Theorem 4.2, p. 13 (the case `ε = 0`): under Assumption 4.1, (10) with
`ε = 0` is the sample average `(1/N) Σ ℓ(ξ̂ᵢ)`, the objective of (12b) at `ε = 0` converges
to that sample average as `λ → ∞`, and (12a) holds with equality at `ε = 0`. -/
theorem worstCase_eq_sampleAverage_of_zero {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E] [FiniteDimensional ℝ E]
    [MeasurableSpace E] [BorelSpace E]
    {K N : ℕ} (hK : 0 < K) (hN : 0 < N) (Ξ : Set E) (ℓ : Fin K → E → EReal)
    (hmeas : ∀ k, Measurable (ℓ k)) (ξhat : Fin N → E) (hξ : ∀ i, ξhat i ∈ Ξ)
    (hA : Assumption41 Ξ ℓ) :
    worstCaseExpectation 0 Ξ ξhat (maxLoss ℓ)
        = ((1 / (N : ℝ) : ℝ) : EReal) * (∑ i, maxLoss ℓ (ξhat i)) ∧
      Tendsto (fun lam : ℝ => ((1 / (N : ℝ) : ℝ) : EReal) *
          ∑ i, (⨆ ξ ∈ Ξ, maxLoss ℓ ξ - ((lam * ‖ξ - ξhat i‖ : ℝ) : EReal)))
        atTop (𝓝 (((1 / (N : ℝ) : ℝ) : EReal) * (∑ i, maxLoss ℓ (ξhat i)))) ∧
      worstCaseExpectation 0 Ξ ξhat (maxLoss ℓ) = program12cValue 0 Ξ ξhat (maxLoss ℓ) := by sorry

end WassDDRO.Reduction
Source
Mohajerin Esfahani & Kuhn, arXiv:1505.05116v3, proof of Theorem 4.2, p. 13 (the case ε = 0)
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