Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 4.2, (12a)–(12c), p. 12 — the worst-case expectation is at most the value of (12c)

Proved
WassDDRO.Reduction.worstCase_le_program12c

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

distributionally-robust-optimizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1wassersteinweak-duality

Let EEE be a finite-dimensional real normed space with its Borel σ-algebra, Ξ⊆E\Xi\subseteq EΞ⊆E, and let ℓ1,…,ℓK:E→R‾\ell_1,\dots,\ell_K:E\to\overline{\mathbb R}ℓ1​,…,ℓK​:E→R (K≥1K\ge1K≥1) be measurable, with ℓ=max⁡kℓk\ell=\max_k\ell_kℓ=maxk​ℓk​. Let ξ^1,…,ξ^N∈Ξ\hat\xi_1,\dots,\hat\xi_N\in\Xiξ^​1​,…,ξ^​N​∈Ξ (N≥1N\ge 1N≥1) be samples with empirical distribution P^N\widehat{\mathbb P}_NPN​, and let ε≥0\varepsilon\ge 0ε≥0. Then, without any convexity assumption,

sup⁡Q∈Bε(P^N)EQ[ℓ(ξ)]  ≤  {inf⁡λ,siλε+1N∑i=1Nsis.t.sup⁡ξ∈Ξ(ℓ(ξ)−λ∥ξ−ξ^i∥)≤si∀i≤Nλ≥0.\sup_{\mathbb Q\in\mathbb B_\varepsilon(\widehat{\mathbb P}_N)}\mathbb E^{\mathbb Q}[\ell(\xi)]\;\le\;\left\{\begin{array}{ll}\inf\limits_{\lambda,s_i}&\lambda\varepsilon+\frac1N\sum_{i=1}^N s_i\\ \text{s.t.}&\sup_{\xi\in\Xi}\big(\ell(\xi)-\lambda\|\xi-\hat\xi_i\|\big)\le s_i\quad\forall i\le N\\ &\lambda\ge 0.\end{array}\right.Q∈Bε​(PN​)sup​EQ[ℓ(ξ)]≤⎩⎨⎧​λ,si​inf​s.t.​λε+N1​∑i=1N​si​supξ∈Ξ​(ℓ(ξ)−λ∥ξ−ξ^​i​∥)≤si​∀i≤Nλ≥0.​

This is the weak-duality half of the reduction: the right-hand side is (12c), the epigraph form of (12b), obtained from (10) by the max-min inequality (12a).

Formalization Note The expectation follows the paper's extended-arithmetic convention (∞−∞=∞\infty-\infty=\infty∞−∞=∞); the infimum is +∞+\infty+∞ when (12c) is infeasible. The sample condition ξ^i∈Ξ\hat\xi_i\in\Xiξ^​i​∈Ξ and measurability of the ℓk\ell_kℓk​ are the paper's standing assumptions (§2, p. 5; p. 11).

Preamble
import Mathlib
import Definitions.Def_WassDDRO_Reduction_Setting

open MeasureTheory Filter Topology
Formal statement
namespace WassDDRO.Reduction

/-- Proof of Theorem 4.2, (12a)–(12c), p. 12: without Assumption 4.1, the worst-case
expectation (10) is at most the optimal value of (12c). -/
theorem worstCase_le_program12c {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)
    (ε : ℝ) (hε : 0 ≤ ε) :
    worstCaseExpectation ε Ξ ξhat (maxLoss ℓ) ≤ program12cValue ε Ξ ξhat (maxLoss ℓ) := by sorry

end WassDDRO.Reduction
Source
Mohajerin Esfahani & Kuhn, arXiv:1505.05116v3, proof of Theorem 4.2, (12a), (12b), (12c), p. 12
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