Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Corollary 4.3, p. 14 — (10) ≤ optimal value of (12f) for any ε ≥ 0, without Assumption 4.1

Proved
WassDDRO.Reduction.corollary_4_3

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

convex-conjugatedistributionally-robust-optimizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1upper-boundwasserstein

Let EEE be a finite-dimensional real normed space with its Borel σ-algebra and dual norm ∥⋅∥∗\|\cdot\|_*∥⋅∥∗​, Ξ⊆E\Xi\subseteq EΞ⊆E, measurable ℓ1,…,ℓK:E→R‾\ell_1,\dots,\ell_K:E\to\overline{\mathbb R}ℓ1​,…,ℓK​:E→R (K≥1K\ge1K≥1) with ℓ=max⁡kℓk\ell=\max_k\ell_kℓ=maxk​ℓk​, samples ξ^1,…,ξ^N∈Ξ\hat\xi_1,\dots,\hat\xi_N\in\Xiξ^​1​,…,ξ^​N​∈Ξ (N≥1N\ge1N≥1) and ε≥0\varepsilon\ge0ε≥0. Then the worst-case expectation (10) is at most the optimal value of the finite convex program (12f):

sup⁡Q∈Bε(P^N)EQ[ℓ(ξ)]  ≤  {inf⁡λ,si,zikλε+1N∑i=1Nsis.t.[−ℓk+χΞ]∗(zik)−⟨zik,ξ^i⟩≤si∀i≤N, ∀k≤K∥zik∥∗≤λ∀i≤N, ∀k≤K.\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,z_{ik}}&\lambda\varepsilon+\frac1N\sum_{i=1}^N s_i\\ \text{s.t.}&[-\ell_k+\chi_\Xi]^*(z_{ik})-\langle z_{ik},\hat\xi_i\rangle\le s_i\quad\forall i\le N,\ \forall k\le K\\ &\|z_{ik}\|_*\le\lambda\quad\forall i\le N,\ \forall k\le K.\end{array}\right.Q∈Bε​(PN​)sup​EQ[ℓ(ξ)]≤⎩⎨⎧​λ,si​,zik​inf​s.t.​λε+N1​∑i=1N​si​[−ℓk​+χΞ​]∗(zik​)−⟨zik​,ξ^​i​⟩≤si​∀i≤N, ∀k≤K∥zik​∥∗​≤λ∀i≤N, ∀k≤K.​

No convexity of Ξ\XiΞ or of the −ℓk-\ell_k−ℓk​ is assumed.

This gives a computable conservative bound on the worst-case expectation for arbitrary piecewise losses.

Formalization Note Here [−ℓk+χΞ]∗(z)=sup⁡ξ∈Ξ(⟨z,ξ⟩+ℓk(ξ))[-\ell_k+\chi_\Xi]^*(z)=\sup_{\xi\in\Xi}\big(\langle z,\xi\rangle+\ell_k(\xi)\big)[−ℓk​+χΞ​]∗(z)=supξ∈Ξ​(⟨z,ξ⟩+ℓk​(ξ)), which is the paper's reading of the sum under ∞−∞=∞\infty-\infty=\infty∞−∞=∞ (no EReal addition is performed). The infimum is +∞+\infty+∞ when (12f) is infeasible.

Preamble
import Mathlib
import Definitions.Def_WassDDRO_Reduction_Setting

open MeasureTheory Filter Topology
Formal statement
namespace WassDDRO.Reduction

/-- Corollary 4.3 (Approximate convex reduction), p. 14: for any `ε ≥ 0`, without
Assumption 4.1, the worst-case expectation (10) is at most the optimal value of (12f). -/
theorem corollary_4_3 {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) ≤ program12fValue ε Ξ ξhat ℓ := by sorry

end WassDDRO.Reduction
Source
Mohajerin Esfahani & Kuhn, arXiv:1505.05116v3, Corollary 4.3, p. 14; program (12f), p. 13
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