Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Appendix A — D_n(F) = s(0) = s(E Σσ_i)

Proved
RadGauss.Discrepancy.discrepancy_eq_condSup_zero

by mikedeng1 · Oct 5, 2026 · Mathlib 0df444a (Lean v4.33.1)

learning-theorymaximum-discrepancyp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1rademacher-complexity

Let μ\muμ be a probability measure on X\mathcal XX, let n=2mn = 2mn=2m with m≥1m \ge 1m≥1, and let FFF be a nonempty class of measurable functions X→[−1,1]\mathcal X \to [-1,1]X→[−1,1]. Then the expected maximum discrepancy equals the conditional supremum function at zero:

Dn(F)=s(0)=s ⁣(E∑i=1nσi).D_n(F) = s(0) = s\!\left(\mathbf E\sum_{i=1}^n\sigma_i\right).Dn​(F)=s(0)=s(Ei=1∑n​σi​).

The identity expresses the fact that, because X1,…,XnX_1,\dots,X_nX1​,…,Xn​ are i.i.d., every balanced split of the sample into two halves is equivalent to the fixed split used in the definition of D^n\hat D_nD^n​.

Formalization Note Stated as Dn(F)=s(0)D_n(F) = s(0)Dn​(F)=s(0); E∑iσi=0\mathbf E\sum_i\sigma_i = 0E∑i​σi​=0. The sample size is even (n=2mn = 2mn=2m) because D^n\hat D_nD^n​ needs half sums. Added hypotheses as for the other statements: FFF nonempty, members measurable, and measurability of x↦sup⁡f∈F∑iσif(xi)x\mapsto\sup_{f\in F}\sum_i\sigma_i f(x_i)x↦supf∈F​∑i​σi​f(xi​) for every sign vector.

Preamble
import Definitions.Def_RadGauss_RiskBound_rademacherComplexity
import Definitions.Def_RadGauss_Discrepancy_maxDiscrepancy
import Definitions.Def_RadGauss_Discrepancy_condSup

open MeasureTheory
open scoped ENNReal Pointwise
Formal statement
namespace RadGauss.Discrepancy

/-- Appendix A, p. 479: `D_n(F) = s(0) = s(E Σ_i σ_i)` for `n = 2m`. -/
theorem discrepancy_eq_condSup_zero {X : Type*} [MeasurableSpace X] (μ : Measure X)
    [IsProbabilityMeasure μ] (m : ℕ) (hm : 0 < m) (F : Set (X → ℝ)) (hFne : F.Nonempty)
    (hFrange : ∀ f ∈ F, ∀ x, f x ∈ Set.Icc (-1 : ℝ) 1)
    (hFmeas : ∀ f ∈ F, Measurable f)
    (hsup : ∀ σ : Fin (2 * m) → Bool,
      Measurable fun x : Fin (2 * m) → X => ⨆ f : F, ∑ i, RadGauss.RiskBound.signVal (σ i) * (f : X → ℝ) (x i)) :
    expectedMaxDiscrepancy μ m F = condSup μ (2 * m) F 0 := by sorry

end RadGauss.Discrepancy
Source
Bartlett, Mendelson, Rademacher and Gaussian Complexities: Risk Bounds and Structural Results, J. Mach. Learn. Res. 3 (2002), p. 479 (PDF p. 17), Appendix A, display after the first display
Human review
  • Endorsed by Shuze Chen · Oct 5, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 5, 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