Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 4.1: if h₁, h₂, h₃ have error ≤ β on D, D₂, D₃, then majority(h₁, h₂, h₃) has error ≤ g(β) = 3β² − 2β³ on D

Proved
ComputationalLearning.modest_boosting

by naimengye · Sep 24, 2026 · Mathlib 0df444a (Lean v4.33.1)

boostingmajority-voteprobability

Lemma 4.1. Let g(β)=3β2−2β3g(\beta) = 3\beta^2 - 2\beta^3g(β)=3β2−2β3. Let the distributions DDD, D2D_2D2​ and D3D_3D3​ be as defined above, and let h1,h2h_1, h_2h1​,h2​ and h3h_3h3​ satisfy errorD(h1)≤β\mathrm{error}_D(h_1) \le \betaerrorD​(h1​)≤β, errorD2(h2)≤β\mathrm{error}_{D_2}(h_2) \le \betaerrorD2​​(h2​)≤β and errorD3(h3)≤β\mathrm{error}_{D_3}(h_3) \le \betaerrorD3​​(h3​)≤β. Then if h=majority(h1,h2,h3)h = \mathrm{majority}(h_1, h_2, h_3)h=majority(h1​,h2​,h3​), errorD(h)≤g(β)\mathrm{error}_D(h) \le g(\beta)errorD​(h)≤g(β).

Formally: for a probability measure DDD, measurable c,h1,h2,h3c, h_1, h_2, h_3c,h1​,h2​,h3​, 0≤β≤1/20 \le \beta \le 1/20≤β≤1/2, with D2=12D[⋅∣h1=c]+12D[⋅∣h1≠c]D_2 = \tfrac12 D[\cdot\mid h_1 = c] + \tfrac12 D[\cdot \mid h_1 \ne c]D2​=21​D[⋅∣h1​=c]+21​D[⋅∣h1​=c] and D3=D[⋅∣h1≠h2]D_3 = D[\cdot \mid h_1 \ne h_2]D3​=D[⋅∣h1​=h2​] (a conditional on a null event being the zero measure), the three error bounds imply errorD(majority(h1,h2,h3))≤3β2−2β3\mathrm{error}_D(\mathrm{majority}(h_1, h_2, h_3)) \le 3\beta^2 - 2\beta^3errorD​(majority(h1​,h2​,h3​))≤3β2−2β3. The degenerate cases (a null conditioning event) are covered: verified exhaustively on random distributions over up to five points, all 23n2^{3n}23n hypothesis triples, no violation.

Preamble
import Definitions.Def_ComputationalLearning_Boosting

open MeasureTheory ProbabilityTheory
Formal statement
namespace ComputationalLearning

/-- **Lemma 4.1** (p. 82). Let `g(β) = 3β² − 2β³`. Let the distributions `D`, `D₂` and `D₃` be as
defined in §4.3.1 (`D₂` filters `D` through `h₁`, `D₃` conditions `D` on `h₁ ≠ h₂`), and let
`h₁, h₂, h₃` satisfy `error_D(h₁) ≤ β`, `error_{D₂}(h₂) ≤ β` and `error_{D₃}(h₃) ≤ β`. Then, for
`h = majority(h₁, h₂, h₃)`, `error_D(h) ≤ g(β)`. Stated for `0 ≤ β ≤ 1/2` and measurable
`c, h₁, h₂, h₃`; when a conditioning event is null the corresponding filtered measure is the zero
measure (or has mass `1/2`), and the bound still holds. -/
theorem modest_boosting {X : Type*} [MeasurableSpace X] (D : Measure X) [IsProbabilityMeasure D]
    (c h₁ h₂ h₃ : X → Bool) (hc : Measurable c) (h₁m : Measurable h₁) (h₂m : Measurable h₂)
    (h₃m : Measurable h₃) {β : ℝ} (hβ0 : 0 ≤ β) (hβ : β ≤ 1 / 2)
    (e₁ : errorOf D c h₁ ≤ β) (e₂ : errorOf (filtered2 D c h₁) c h₂ ≤ β)
    (e₃ : errorOf (filtered3 D h₁ h₂) c h₃ ≤ β) :
    errorOf D c (majority3 h₁ h₂ h₃) ≤ boostFun β := by sorry

end ComputationalLearning
Source
Kearns and Vazirani, An Introduction to Computational Learning Theory, MIT Press 1994, doi:10.7551/mitpress/3897.001.0001, §4.3.1-4.3.2 pp. 79-85, Lemma 4.1 with its proof (Equations (4.1)-(4.7))
Human review
  • Endorsed by Shuze Chen · Sep 25, 2026

    Confirmed by the moderator at approval.

  • Endorsed by naimengye · Sep 25, 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