Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 2, p. 16 — (β, λ) ↦ ℓ_rob(β, λ; x) is convex on B × ℝ₊ for every x

Proved
OTDRO.Cvx.ellRob_convex

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

convex-analysisdistributionally-robust-optimizationoptimal-transportp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let A:Rd→Rd×dA : \mathbb{R}^d \to \mathbb{R}^{d\times d}A:Rd→Rd×d take positive definite values with lower semicontinuous cost c(x,x′)=(x−x′)TA(x)(x−x′)c(x, x') = (x - x')^{\mathsf T}A(x)(x - x')c(x,x′)=(x−x′)TA(x)(x−x′) (Assumption 1a), let ℓ:R→R\ell : \mathbb{R} \to \mathbb{R}ℓ:R→R be convex, δ>0\delta > 0δ>0, and let B⊆RdB \subseteq \mathbb{R}^dB⊆Rd be convex. Then for every x∈Rdx \in \mathbb{R}^dx∈Rd the map (β,λ)↦ℓrob(β,λ;x)(\beta, \lambda) \mapsto \ell_{rob}(\beta, \lambda; x)(β,λ)↦ℓrob​(β,λ;x) is convex on B×R+B \times \mathbb{R}_+B×R+​: for (β1,λ1),(β2,λ2)∈B×R+(\beta_1, \lambda_1), (\beta_2, \lambda_2) \in B \times \mathbb{R}_+(β1​,λ1​),(β2​,λ2​)∈B×R+​ and α∈[0,1]\alpha \in [0, 1]α∈[0,1],

ℓrob(αβ1+(1−α)β2, αλ1+(1−α)λ2; x)≤α ℓrob(β1,λ1;x)+(1−α) ℓrob(β2,λ2;x).\ell_{rob}\big(\alpha\beta_1 + (1-\alpha)\beta_2,\ \alpha\lambda_1 + (1-\alpha)\lambda_2;\ x\big) \le \alpha\,\ell_{rob}(\beta_1, \lambda_1; x) + (1-\alpha)\,\ell_{rob}(\beta_2, \lambda_2; x).ℓrob​(αβ1​+(1−α)β2​, αλ1​+(1−α)λ2​; x)≤αℓrob​(β1​,λ1​;x)+(1−α)ℓrob​(β2​,λ2​;x).

Pointwise convexity of the robust loss is the step from which convexity of the dual objective fδf_\deltafδ​ follows by integration.

Formalization Note ℓrob\ell_{rob}ℓrob​ takes values in (−∞,+∞](-\infty, +\infty](−∞,+∞], so convexity is written as the displayed inequality in EReal rather than with ConvexOn; with Mathlib's convention 0⋅(+∞)=00 \cdot (+\infty) = 00⋅(+∞)=0 the inequality reduces to an equality at α∈{0,1}\alpha \in \{0, 1\}α∈{0,1}. The paper assumes "Assumptions 1a and 2"; only the convexity of ℓ\ellℓ from Assumption 2 is kept, and Assumption 1(b) is not assumed, which makes the statement stronger. No probability measure appears.

Preamble
import Mathlib
import Definitions.Def_OTDRO_Dual_Setting
Formal statement
namespace OTDRO.Cvx

open Matrix

/-- **Lemma 2**, p. 16: under Assumption 1a (`A(x)` positive definite for every `x`, the cost
lower semicontinuous) and the convexity of `ℓ` from Assumption 2, the map
`(β, λ) ↦ ℓ_rob(β, λ; x)` is convex on `B × ℝ₊` for every `x ∈ ℝ^d`. Convexity of the
`EReal`-valued map is written out: for `θᵢ = (βᵢ, λᵢ) ∈ B × ℝ₊` and `α ∈ [0, 1]`,
`ℓ_rob(αθ₁ + (1 − α)θ₂; x) ≤ α ℓ_rob(θ₁; x) + (1 − α) ℓ_rob(θ₂; x)`. -/
theorem ellRob_convex {d : ℕ}
    (A : EuclideanSpace ℝ (Fin d) → Matrix (Fin d) (Fin d) ℝ)
    (hPD : ∀ x, (A x).PosDef)
    (hlsc : LowerSemicontinuous (fun p : EuclideanSpace ℝ (Fin d) × EuclideanSpace ℝ (Fin d) =>
      OTDRO.Dual.mahalCost A p.1 p.2))
    (ℓ : ℝ → ℝ) (hℓ : ConvexOn ℝ Set.univ ℓ) (δ : ℝ) (hδ : 0 < δ)
    (B : Set (EuclideanSpace ℝ (Fin d))) (hB : Convex ℝ B) :
    ∀ x : EuclideanSpace ℝ (Fin d),
      ∀ β₁ ∈ B, ∀ β₂ ∈ B, ∀ lam₁ lam₂ : ℝ, 0 ≤ lam₁ → 0 ≤ lam₂ →
      ∀ α : ℝ, 0 ≤ α → α ≤ 1 →
        OTDRO.Dual.ellRob ℓ A δ (α • β₁ + (1 - α) • β₂) (α * lam₁ + (1 - α) * lam₂) x ≤
          (α : EReal) * OTDRO.Dual.ellRob ℓ A δ β₁ lam₁ x +
            ((1 - α : ℝ) : EReal) * OTDRO.Dual.ellRob ℓ A δ β₂ lam₂ x := by sorry

end OTDRO.Cvx
Source
arXiv:1810.02403v3, Lemma 2, p. 16 (proof in §5.1, p. 32)
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