Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 10, p. 25 — moment-set support formula and value at risk guarantee

Proved
DataDrivenRO.Moment.theorem_10

by mikedeng1 · Oct 5, 2026 · Mathlib 0df444a (Lean v4.33.1)

moment-uncertaintyp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1robust-optimizationvalue-at-risk

Fix R≥0R\ge0R≥0, nonnegative moment thresholds Γ1,Γ2\Gamma_1,\Gamma_2Γ1​,Γ2​, estimates μ^,Σ^\hat\mu,\hat\Sigmaμ^​,Σ^, a factor CCC with C⊤C=Σ^+Γ2IC^\top C=\hat\Sigma+\Gamma_2IC⊤C=Σ^+Γ2​I, and 0<ε<10<\varepsilon<10<ε<1. For the moment uncertainty set UεCS\mathcal U^{CS}_{\varepsilon}UεCS​ of (35), every v∈Rdv\in\mathbb R^dv∈Rd satisfies

δ∗(v∣UεCS)=μ^⊤v+Γ1∥v∥2+1−εεv⊤(Σ^+Γ2I)v.\delta^*(v\mid\mathcal U^{CS}_{\varepsilon}) =\hat\mu^\top v+\Gamma_1\|v\|_2+ \sqrt{\frac{1-\varepsilon}{\varepsilon}} \sqrt{v^\top(\hat\Sigma+\Gamma_2I)v}.δ∗(v∣UεCS​)=μ^​⊤v+Γ1​∥v∥2​+ε1−ε​​v⊤(Σ^+Γ2​I)v​.

For every P∈PCSP\in\mathcal P^{CS}P∈PCS, its VaR⁡εP(v)\operatorname{VaR}^P_{\varepsilon}(v)VaRεP​(v) is at most this value. The set UεCS\mathcal U^{CS}_{\varepsilon}UεCS​ is nonempty, convex and compact. Thus its support function meets the deterministic criterion of Theorem 1 for every law in the moment region.

Formalization Note This is the deterministic content of Theorem 10 after the sampling data and thresholds are fixed. The paper's statement that the whole family works with sampling probability at least 1−α1-\alpha1−α depends on coverage of the confidence region. The bootstrap coverage described on p. 25 is approximate and is not asserted here. Equation (34)'s printed worst-case equality is used only in its upper-bound direction because the confidence region also imposes ball support. Fin d is zero-based, and the Lean function type uses an explicit Euclidean norm rather than its default sup norm.


Retired 2026-10-27: a Lean-vs-paper fidelity audit found this statement weaker than, or narrower than, the cited result. A corrected statement will be resubmitted.

Preamble
import Mathlib
import Definitions.Def_DataDrivenRO_Moment_Setting
Formal statement
namespace DataDrivenRO.Moment

/-- The deterministic content of Theorem 10, p. 25: the support formula,
the (34) upper bound for every distribution in the moment region, and the
geometry required to obtain the probabilistic guarantee by Theorem 1. -/
theorem theorem_10 {d : ℕ} (R Γ₁ Γ₂ : ℝ)
    (μhat : Fin d → ℝ) (Shat C : Matrix (Fin d) (Fin d) ℝ)
    (hR : 0 ≤ R) (hΓ₁ : 0 ≤ Γ₁) (hΓ₂ : 0 ≤ Γ₂)
    (hC : C.transpose * C = Shat + Γ₂ • (1 : Matrix (Fin d) (Fin d) ℝ))
    (ε : ℝ) (hε0 : 0 < ε) (hε1 : ε < 1) :
    (∀ v : Fin d → ℝ,
      RobustMDP.Shared.supportFunction (UCS μhat C Γ₁ ε) v =
        csValue μhat Shat Γ₁ Γ₂ ε v) ∧
    (∀ P ∈ PCS R Γ₁ Γ₂ μhat Shat, ∀ v : Fin d → ℝ,
      VaR P ε v ≤ csValue μhat Shat Γ₁ Γ₂ ε v) ∧
    (UCS μhat C Γ₁ ε).Nonempty ∧
    Convex ℝ (UCS μhat C Γ₁ ε) ∧
    IsCompact (UCS μhat C Γ₁ ε) := by sorry

end DataDrivenRO.Moment
Source
Bertsimas, Gupta & Kallus, Data-Driven Robust Optimization, arXiv:1401.0212v2, Theorem 10 and (34)–(35), p. 25; proof EC.1.7, p. ec8
Human review
  • Endorsed by Shuze Chen · Oct 5, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 5, 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