Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 2 (Strong LDP), (9), p. 13 — ℙ^∞(ℙ̂_T ∈ 𝒟) ≤ (T+1)^d e^{−T inf_{ℙ′∈𝒟} I(ℙ′,ℙ)} for all T ≥ 1

Proved
DROOptimal.Predictor.theorem_2

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

large-deviationsmethod-of-typesp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1probabilityrelative-entropy

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 ξ1,…,ξT\xi_1,\dots,\xi_Tξ1​,…,ξT​. Then for every Borel set D⊆P\mathcal D\subseteq\mathcal PD⊆P and every T≥1T\ge1T≥1,

P∞(P^T∈D)≤(T+1)d e−Tinf⁡P′∈DI(P′,P),\mathbb P^\infty\big(\hat{\mathbb P}_T\in\mathcal D\big)\le (T+1)^d\,e^{-T\inf_{\mathbb P'\in\mathcal D}I(\mathbb P',\mathbb P)} ,P∞(P^T​∈D)≤(T+1)de−TinfP′∈D​I(P′,P),

where III is the relative entropy and e−∞=0e^{-\infty}=0e−∞=0.

This is the finite-sample (method of types) form of Sanov's theorem; it gives the finite-sample guarantee of Theorem 5.

Formalization Note The infimum is taken in the extended reals (it is +∞+\infty+∞ for empty D\mathcal DD). The bound is stated for every real s≤inf⁡P′∈DI(P′,P)s\le\inf_{\mathbb P'\in\mathcal D}I(\mathbb P',\mathbb P)s≤infP′∈D​I(P′,P) as P∞(P^T∈D)≤(T+1)de−Ts\mathbb P^\infty(\hat{\mathbb P}_T\in\mathcal D)\le(T+1)^de^{-Ts}P∞(P^T​∈D)≤(T+1)de−Ts; this is the displayed inequality when the infimum is finite, and forces probability 000 when it is +∞+\infty+∞. Borel means MeasurableSet D in the simplex subtype. The paper writes ∀T∈N\forall T\in\mathbb N∀T∈N; the empirical distribution is defined for T≥1T\ge1T≥1 only, so T≥1T\ge1T≥1 is assumed.

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

/-- Theorem 2 (Strong LDP), (9), p. 13: if the samples are drawn independently from ℙ ∈ 𝒫, then for
every Borel set 𝒟 ⊆ 𝒫 and every T ≥ 1,
ℙ^∞(ℙ̂_T ∈ 𝒟) ≤ (T + 1)^d e^{−T inf_{ℙ′ ∈ 𝒟} I(ℙ′, ℙ)}.
The infimum lives in `EReal` (it is +∞ when 𝒟 is empty or I(·, ℙ) ≡ ∞ on 𝒟, and then the bound is 0);
the bound is stated for every real s ≤ inf_{ℙ′ ∈ 𝒟} I(ℙ′, ℙ). -/
theorem theorem_2 {d : ℕ} (ℙ : Δ d) (D : Set (Δ d)) (hD : MeasurableSet D)
    (T : ℕ) (hT : 1 ≤ T) (s : ℝ)
    (hs : (s : EReal) ≤ ⨅ ℙ' ∈ D, relEntropy ℙ' ℙ) :
    empProb ℙ T D ≤ ((T : ℝ) + 1) ^ d * Real.exp (-((T : ℝ) * s)) := by sorry

end DROOptimal.Predictor
Source
Van Parys, Mohajerin Esfahani & Kuhn, From Data to Decisions: Distributionally Robust Optimization is Optimal, arXiv:1704.04118v3, p. 13, Theorem 2, (9)
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