Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§3, p. 224, proof of Lemma 3.1 — a mistake of WML multiplies the total weight by at most u = (1+β)/2 + (1−β)γ

Proved
WeightedMajority.Shifting.lemma_3_1_ratio

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

mistake-boundonline-learningp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1weighted-majority

Let 0<β<10 < \beta < 10<β<1 and 0≤γ<120 \le \gamma < \tfrac120≤γ<21​, and consider a run of the algorithm WML with parameters β,γ\beta, \gammaβ,γ on a pool of nnn algorithms and an arbitrary sequence of binary-labelled trials. Write W(t)W^{(t)}W(t) for the total weight of the pool at the beginning of trial ttt. If the master algorithm makes a mistake in trial ttt, then

W(t+1)≤(1+β2+(1−β)γ)W(t).W^{(t+1)} \le \left(\frac{1+\beta}{2} + (1-\beta)\gamma\right) W^{(t)} .W(t+1)≤(21+β​+(1−β)γ)W(t).

This is the per-mistake contraction step of the proof of Lemma 3.1: members whose weight is at most γ/n\gamma/nγ/n times the total are protected from the update, and their total weight is at most γW(t)\gamma W^{(t)}γW(t), which is what the extra term (1−β)γ(1-\beta)\gamma(1−β)γ accounts for. Since γ<1/2\gamma < 1/2γ<1/2, the factor is less than 111.

Formalization Note W(t)W^{(t)}W(t) is totalWeight (w t) and the factor is uFactor β γ. The run's initial weights are positive, as WML requires.

Preamble
import Mathlib
import Definitions.Def_WeightedMajority_Shifting_WML
Formal statement
namespace WeightedMajority.Shifting

theorem lemma_3_1_ratio {n T : ℕ} {β γ : ℝ} (hβ0 : 0 < β) (hβ1 : β < 1)
    (hγ0 : 0 ≤ γ) (hγ1 : γ < 1 / 2)
    (x : Fin T → Fin n → Bool) (ρ : Fin T → Bool) (w : ℕ → Fin n → ℝ) (lam : Fin T → Bool)
    (hrun : IsWMLRun β γ x ρ w lam) (t : Fin T) (hmis : lam t ≠ ρ t) :
    totalWeight (w ((t : ℕ) + 1)) ≤ uFactor β γ * totalWeight (w t) := by sorry

end WeightedMajority.Shifting
Source
Littlestone, Warmuth, The Weighted Majority Algorithm, Inform. and Comput. 108 (1994), p. 224, Section 3, proof of Lemma 3.1
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