Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 1 (Weak LDP), (7a), p. 12 — limsup (1/T) log ℙ^∞(ℙ̂_T ∈ 𝒟) ≤ −inf_{ℙ′∈𝒟} I(ℙ′,ℙ)

Proved
DROOptimal.Predictor.theorem_1_upper

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

large-deviationsp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1probabilityrelative-entropysanov-theorem

Let ξ1,ξ2,…\xi_1,\xi_2,\dotsξ1​,ξ2​,… be drawn independently from a distribution P\mathbb PP on Ξ={1,…,d}\Xi=\{1,\dots,d\}Ξ={1,…,d}, and let P^T\hat{\mathbb P}_TP^T​ be the empirical distribution of the first TTT samples. Then for every Borel set D⊆P\mathcal D\subseteq\mathcal PD⊆P,

lim sup⁡T→∞1Tlog⁡P∞(P^T∈D)≤−inf⁡P′∈DI(P′,P).\limsup_{T\to\infty}\frac1T\log\mathbb P^\infty\big(\hat{\mathbb P}_T\in\mathcal D\big)\le-\inf_{\mathbb P'\in\mathcal D}I(\mathbb P',\mathbb P).T→∞limsup​T1​logP∞(P^T​∈D)≤−P′∈Dinf​I(P′,P).

This large deviation upper bound is what makes c^r\hat c_rc^r​ feasible in (5) (Theorem 3).

Formalization Note The statement is logarithm-free: for every real s<inf⁡P′∈DI(P′,P)s<\inf_{\mathbb P'\in\mathcal D}I(\mathbb P',\mathbb P)s<infP′∈D​I(P′,P) (an extended real), eventually P∞(P^T∈D)≤e−sT\mathbb P^\infty(\hat{\mathbb P}_T\in\mathcal D)\le e^{-sT}P∞(P^T​∈D)≤e−sT. This is equivalent to the displayed bound with log⁡0=−∞\log0=-\inftylog0=−∞, including the case of an infinite infimum. Borel means MeasurableSet D in the simplex subtype.

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

/-- Theorem 1 (Weak LDP), (7a), p. 12: if the samples are drawn independently from ℙ ∈ 𝒫, then for
every Borel set 𝒟 ⊆ 𝒫,
limsup_{T→∞} (1/T) log ℙ^∞(ℙ̂_T ∈ 𝒟) ≤ − inf_{ℙ′ ∈ 𝒟} I(ℙ′, ℙ),
stated without logarithms: for every real s below the (`EReal`) infimum, eventually
ℙ^∞(ℙ̂_T ∈ 𝒟) ≤ e^{−sT}. -/
theorem theorem_1_upper {d : ℕ} (ℙ : Δ d) (D : Set (Δ d)) (hD : MeasurableSet D) (s : ℝ)
    (hs : (s : EReal) < ⨅ ℙ' ∈ D, relEntropy ℙ' ℙ) :
    ∀ᶠ T : ℕ in Filter.atTop, empProb ℙ T D ≤ Real.exp (-(s * (T : 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. 12, Theorem 1, (7a); proof in Appendix A, pp. 27–28
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