Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 3, p. 16 — for r ≄ 0 the distributionally robust predictor ĉ_r is continuous on X Ɨ š’«

Proved
DROOptimal.Predictor.proposition_3

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

continuitydistributionally-robust-optimizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1relative-entropy

Let XāŠ†RnX\subseteq\mathbb R^nXāŠ†Rn be compact, Īž={1,…,d}\Xi=\{1,\dots,d\}Īž={1,…,d}, γ:XĆ—Īžā†’R\gamma:X\times\Xi\to\mathbb Rγ:XĆ—Īžā†’R continuous in xxx for each iii, and let

c^r(x,P′)=sup⁔P∈P{c(x,P):I(P′,P)≤r}\hat c_r(x,\mathbb P')=\sup_{\mathbb P\in\mathcal P}\{c(x,\mathbb P): I(\mathbb P',\mathbb P)\le r\}c^r​(x,P′)=P∈Psup​{c(x,P):I(P′,P)≤r}

be the distributionally robust predictor (10). If r≄0r\ge0r≄0, then c^r\hat c_rc^r​ is (jointly) continuous on XƗPX\times\mathcal PXƗP; that is, c^r\hat c_rc^r​ belongs to the class C\mathcal CC of data-driven predictors.

Continuity is half of feasibility in (5) and is needed for c^r\hat c_rc^r​ to be a competitor at all.

Formalization Note Continuity is with respect to the product of the subspace topologies on XXX and on the simplex P\mathcal PP.

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

/-- Proposition 3 (Continuity of ĉ_r), p. 16: under the standing assumptions of §2 (p. 5), if r ≄ 0
then the distributionally robust predictor ĉ_r is continuous on X Ɨ š’«. -/
theorem proposition_3 {n d : ā„•} (X : Set (EuclideanSpace ā„ (Fin n))) (hX : IsCompact X)
    (γ : ↄX → Fin d → ā„) (hγ : āˆ€ i, Continuous (fun x : ↄX => γ x i))
    (r : ā„) (hr : 0 ≤ r) :
    IsPredictor (drPredictor γ r) := by sorry

end DROOptimal.Predictor
Source
Van Parys, Mohajerin Esfahani & Kuhn, From Data to Decisions: Distributionally Robust Optimization is Optimal, arXiv:1704.04118v3, p. 16, Proposition 3 (and Remark 2, p. 15, for r = 0)
Human review
  • Endorsed by Shuze Chen Ā· Oct 8, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 Ā· 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
Ā© 2026 Prove2Me