Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 3.7, p. 9 — any data-dependent Q̂_N ∈ B_{ε_N(β_N)}(P̂_N) converges to P in d_W, P^∞-almost surely

Proved
WassDDRO.Consistency.lemma_3_7

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

borel-cantellimeasure-concentrationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1wasserstein

Let EEE be a finite-dimensional real normed space with its Borel σ\sigmaσ-algebra, m=dim⁡E≠2m=\dim E\ne2m=dimE=2, and PPP a probability distribution on EEE supported on Ξ\XiΞ. Suppose Assumption 3.3 holds with exponent a>1a>1a>1, and let c1,c2>0c_1,c_2>0c1​,c2​>0 be constants for which the concentration inequality (7) holds. Let βN∈(0,1)\beta_N\in(0,1)βN​∈(0,1), N∈NN\in\mathbb NN∈N, satisfy

∑N=1∞βN<∞andlim⁡N→∞εN(βN)=0,\sum_{N=1}^\infty\beta_N<\infty\qquad\text{and}\qquad\lim_{N\to\infty}\varepsilon_N(\beta_N)=0,N=1∑∞​βN​<∞andN→∞lim​εN​(βN​)=0,

with εN(β)\varepsilon_N(\beta)εN​(β) the radius (8). Let Q^N\widehat Q_NQ​N​, N≥1N\ge1N≥1, be any distributions, possibly depending on the training data, with Q^N∈BεN(βN)(P^N)\widehat Q_N\in\mathbb B_{\varepsilon_N(\beta_N)}(\widehat P_N)Q​N​∈BεN​(βN​)​(PN​), where P^N\widehat P_NPN​ is the empirical distribution of the first NNN samples of the i.i.d. sequence ξ^1,ξ^2,…∼P\hat\xi_1,\hat\xi_2,\ldots\sim Pξ^​1​,ξ^​2​,…∼P. Then

P∞{lim⁡N→∞dW(P,Q^N)=0}=1.P^\infty\Big\{\lim_{N\to\infty}d_W\big(P,\widehat Q_N\big)=0\Big\}=1 .P∞{N→∞lim​dW​(P,Q​N​)=0}=1.

Every distribution in the shrinking Wasserstein balls thus converges to the true distribution; this is the step in the proof of Theorem 3.6 that turns worst-case expectations into true expectations in the limit.

Formalization Note The selection Q^N(ω)\widehat Q_N(\omega)Q​N​(ω) is any function of the whole sample sequence ω\omegaω that lies in the ball whenever the samples lie in Ξ\XiΞ (as they do P∞P^\inftyP∞-almost surely); in the paper it may depend on the training data. "Almost surely" is stated as a P∞P^\inftyP∞-almost-everywhere statement. c1,c2c_1,c_2c1​,c2​ are any constants satisfying (7), which Theorem 3.4 provides for m≠2m\ne2m=2. The paper's parenthetical "and thus weakly" is a remark citing the literature and is not part of the statement.

Preamble
import Mathlib
import Definitions.Def_WassDDRO_Consistency_Setting

open MeasureTheory Filter Topology
Formal statement
namespace WassDDRO.Consistency

/-- Lemma 3.7 (Convergence of distributions), p. 9. Under Assumption 3.3, with constants
`c₁, c₂` for which (7) holds (`m ≠ 2`), and `β_N ∈ (0, 1)` summable with `ε_N(β_N) → 0`,
any (data-dependent) selection `Q̂_N ∈ B_{ε_N(β_N)}(P̂_N)` satisfies
`P^∞{lim_N d_W(P, Q̂_N) = 0} = 1`. -/
theorem lemma_3_7 {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E] [FiniteDimensional ℝ E]
    [MeasurableSpace E] [BorelSpace E]
    (P : Measure E) [IsProbabilityMeasure P] (Ξ : Set E) (hP : P Ξᶜ = 0)
    (a : ℝ) (ha : 1 < a) (hA : Integrable (fun ξ => Real.exp (‖ξ‖ ^ a)) P)
    (hm : Module.finrank ℝ E ≠ 2)
    (c₁ c₂ : ℝ) (hc₁ : 0 < c₁) (hc₂ : 0 < c₂) (h7 : Concentration7 P a c₁ c₂)
    (β : ℕ → ℝ) (hβ : ∀ N, 0 < β N ∧ β N < 1) (hsum : Summable β)
    (hlim : Tendsto (fun N => radius c₁ c₂ a (Module.finrank ℝ E) N (β N)) atTop (𝓝 0))
    (Qhat : ℕ → (ℕ → E) → Measure E)
    (hQ : ∀ N (ω : ℕ → E), 1 ≤ N → (∀ i, ω i ∈ Ξ) →
      Qhat N ω ∈ WassersteinDRO.Duality.ambiguitySet
        (radius c₁ c₂ a (Module.finrank ℝ E) N (β N)) 1 Ξ
        (WassersteinDRO.Duality.empiricalDistribution (fun i : Fin N => ω i))) :
    ∀ᵐ ω ∂(P_inf P),
      Tendsto (fun N => WassersteinDRO.Duality.wassersteinDistance 1 P (Qhat N ω)) atTop (𝓝 0) := by sorry

end WassDDRO.Consistency
Source
Mohajerin Esfahani & Kuhn, arXiv:1505.05116v3, Lemma 3.7, p. 9
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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