Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 2, (11), p. 15 — ĉ_r(x,ℙ′) = min_{α≥γ̄(x)} α − e^{−r} Π_i (α−γ(x,i))^{ℙ′(i)}, with a bracketed minimizer

Proved
DROOptimal.Predictor.proposition_2

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

distributionally-robust-optimizationdualityp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1relative-entropy

Let X⊆RnX\subseteq\mathbb R^nX⊆Rn be compact, Ξ={1,…,d}\Xi=\{1,\dots,d\}Ξ={1,…,d}, γ:X×Ξ→R\gamma:X\times\Xi\to\mathbb Rγ:X×Ξ→R continuous in xxx for each iii, c(x,P)=∑iP(i)γ(x,i)c(x,\mathbb P)=\sum_i\mathbb P(i)\gamma(x,i)c(x,P)=∑i​P(i)γ(x,i), and let c^r\hat c_rc^r​ be the distributionally robust predictor (10). If r>0r>0r>0 and γˉ(x)=max⁡i∈Ξγ(x,i)\bar\gamma(x)=\max_{i\in\Xi}\gamma(x,i)γˉ​(x)=maxi∈Ξ​γ(x,i) is the worst-case cost, then for every x∈Xx\in Xx∈X and P′∈P\mathbb P'\in\mathcal PP′∈P,

c^r(x,P′)=min⁡α≥γˉ(x) α−e−r∏i∈Ξ(α−γ(x,i))P′(i),\hat c_r(x,\mathbb P')=\min_{\alpha\ge\bar\gamma(x)}\ \alpha-e^{-r}\prod_{i\in\Xi}\big(\alpha-\gamma(x,i)\big)^{\mathbb P'(i)} ,c^r​(x,P′)=α≥γˉ​(x)min​ α−e−ri∈Ξ∏​(α−γ(x,i))P′(i),

and this minimum is attained at some α⋆\alpha^\starα⋆ with

γˉ(x)≤α⋆≤γˉ(x)−e−rc(x,P′)1−e−r.\bar\gamma(x)\le\alpha^\star\le\frac{\bar\gamma(x)-e^{-r}c(x,\mathbb P')}{1-e^{-r}} .γˉ​(x)≤α⋆≤1−e−rγˉ​(x)−e−rc(x,P′)​.

The dual representation reduces the evaluation of c^r\hat c_rc^r​ to a one-dimensional convex problem and is the basis of the continuity of c^r\hat c_rc^r​ (Proposition 3).

Formalization Note "min" is stated as: c^r(x,P′)\hat c_r(x,\mathbb P')c^r​(x,P′) is a value of the objective at some α≥γˉ(x)\alpha\ge\bar\gamma(x)α≥γˉ​(x) and is below all such values. Powers are real powers with 00=10^0=100=1, so outcomes with P′(i)=0\mathbb P'(i)=0P′(i)=0 contribute a factor 111. γˉ(x)\bar\gamma(x)γˉ​(x) is written as sup⁡iγ(x,i)\sup_i\gamma(x,i)supi​γ(x,i), which is the maximum because Ξ\XiΞ is finite and nonempty whenever P\mathcal PP is.

Preamble
import Mathlib
import Definitions.Def_DROOptimal_Predictor_Setting
Formal statement
namespace DROOptimal.Predictor

/-- Proposition 2 (Dual representation of ĉ_r), (11), p. 15: if r > 0 and
γ̄(x) = max_{i ∈ Ξ} γ(x, i), then
ĉ_r(x, ℙ′) = min_{α ≥ γ̄(x)} α − e^{−r} Π_{i ∈ Ξ} (α − γ(x, i))^{ℙ′(i)},
and problem (11) has a minimizer α⋆ with γ̄(x) ≤ α⋆ ≤ (γ̄(x) − e^{−r} c(x, ℙ′)) / (1 − e^{−r}).
Powers are `Real.rpow` (0^0 = 1). -/
theorem proposition_2 {n d : ℕ} (X : Set (EuclideanSpace ℝ (Fin n))) (hX : IsCompact X)
    (γ : ↥X → Fin d → ℝ) (hγ : ∀ i, Continuous (fun x : ↥X => γ x i))
    (r : ℝ) (hr : 0 < r) (x : ↥X) (ℙ' : Δ d) :
    IsLeast {v : ℝ | ∃ α : ℝ, (⨆ i, γ x i) ≤ α ∧
        v = α - Real.exp (-r) * ∏ i, (α - γ x i) ^ ((ℙ' : Fin d → ℝ) i)}
      (drPredictor γ r x ℙ') ∧
    ∃ αstar : ℝ, (⨆ i, γ x i) ≤ αstar ∧
      αstar ≤ ((⨆ i, γ x i) - Real.exp (-r) * cost γ x ℙ') / (1 - Real.exp (-r)) ∧
      drPredictor γ r x ℙ' =
        αstar - Real.exp (-r) * ∏ i, (αstar - γ x i) ^ ((ℙ' : Fin d → ℝ) i) := by sorry

end DROOptimal.Predictor
Source
Van Parys, Mohajerin Esfahani & Kuhn, From Data to Decisions: Distributionally Robust Optimization is Optimal, arXiv:1704.04118v3, p. 15, Proposition 2, (11); proof in Appendix A, p. 28
Human review
  • Endorsed by Shuze Chen · Oct 8, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 8, 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