Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 13, p. 56 — Hoeffding bound 2exp(−2ε²η̂) for the cross-learned mean (1/η̂)(Σ_{i≤η₁} X_i + Σ_{i≤η₂} Y_i/2^ℓ)

Proved
FakeUserRanking.FORC.lemma_13

by mikedeng1 · Oct 24, 2026 · Mathlib 0df444a (Lean v4.33.1)

concentrationcross-learninghoeffdingp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Lemma 13. Fix an integer ℓ>0\ell>0ℓ>0 and η1,η2∈{0,1,…,T}\eta_1,\eta_2\in\{0,1,\dots,T\}η1​,η2​∈{0,1,…,T}, and let

η^=η1+η22ℓ.\hat\eta=\eta_1+\frac{\eta_2}{2^\ell}.η^​=η1​+2ℓη2​​.

Let X1,…,XTX_1,\dots,X_TX1​,…,XT​ and Y1,…,YTY_1,\dots,Y_TY1​,…,YT​ be {0,1}\{0,1\}{0,1}-valued random variables with mean μ\muμ, all 2T2T2T of them independent. If η^>0\hat\eta>0η^​>0, then for every ε>0\varepsilon>0ε>0,

P(∣1η^(∑i=1η1Xi+∑i=1η2Yi2ℓ)−μ∣>ε)≤2exp⁡ ⁣(−2ε2η^).\mathbb P\left(\left|\frac1{\hat\eta}\Big(\sum_{i=1}^{\eta_1}X_i+\sum_{i=1}^{\eta_2}\frac{Y_i}{2^\ell}\Big)-\mu\right|>\varepsilon\right)\le2\exp\!\big(-2\varepsilon^2\hat\eta\big).P(​η^​1​(i=1∑η1​​Xi​+i=1∑η2​​2ℓYi​​)−μ​>ε)≤2exp(−2ε2η^​).

This is the concentration bound behind FORC's cross-learned estimates r^i(ℓ)\hat r^{(\ell)}_ir^i(ℓ)​ of (18), in which level-ℓ\ellℓ samples have weight 111 and lower-level samples weight 2−ℓ2^{-\ell}2−ℓ; it is used in the proof of Lemma 6 (Claim 1, (40)).

Formalization Note. The variables are indexed by Fin T (0-based), and the sums run over the first η1\eta_1η1​ and η2\eta_2η2​ indices. They live on a probability space (Ω,ν)(\Omega,\nu)(Ω,ν), are measurable, take values in {0,1}\{0,1\}{0,1} almost surely and have integral μ\muμ, which makes them identically distributed. Joint independence is iIndepFun of the family indexed by Fin T ⊕ Fin T. Hoeffding's inequality itself is the platform theorem Concentration.hoeffding_two_sided.

Differences from the source:

  • reading: two sequences of {0,1}-valued i.i.d. random variables X_1..X_T and Y_1..Y_T → all 2T variables jointly independent (iIndepFun on Fin T ⊕ Fin T), each {0,1}-valued with mean µ; reason: the proof applies Hoeffding to the X's and Y's together and Claim 1 builds them independent (paper.md Slip 4)
  • encoding: {0,1}-valued random variables with mean µ → measurable functions, almost surely in {0,1}, with ∫ = µ; reason: random variables are measurable; a.s. values and the mean determine the Bernoulli(µ) law, so the variables are identically distributed
  • encoding: indices 1..T; sums Σ_{i=1}^{η_1}, Σ_{i=1}^{η_2} → Fin T, 0-based; sums over indices i < η₁, i < η₂; reason: Lean convention; same instances
Preamble
import Mathlib

open MeasureTheory ProbabilityTheory
Formal statement
namespace FakeUserRanking.FORC

/-- Lemma 13, p. 56: Hoeffding's inequality for the cross-learned weighted mean
`(1/η̂)(∑_{i ≤ η₁} X_i + ∑_{i ≤ η₂} Y_i / 2^ℓ)` with `η̂ = η₁ + η₂/2^ℓ`. -/
theorem lemma_13 {Ω : Type*} [MeasurableSpace Ω] {ν : Measure Ω} [IsProbabilityMeasure ν]
    (T : ℕ) (X Y : Fin T → Ω → ℝ) (μ : ℝ)
    (hindep : iIndepFun (Sum.elim X Y) ν)
    (hXmeas : ∀ i, Measurable (X i)) (hYmeas : ∀ i, Measurable (Y i))
    (hX01 : ∀ i, ∀ᵐ ω ∂ν, X i ω = 0 ∨ X i ω = 1)
    (hY01 : ∀ i, ∀ᵐ ω ∂ν, Y i ω = 0 ∨ Y i ω = 1)
    (hXmean : ∀ i, ∫ ω, X i ω ∂ν = μ) (hYmean : ∀ i, ∫ ω, Y i ω ∂ν = μ)
    (ℓ : ℕ) (hℓ : 0 < ℓ) (η₁ η₂ : ℕ) (h₁ : η₁ ≤ T) (h₂ : η₂ ≤ T)
    (hη : 0 < (η₁ : ℝ) + η₂ / 2 ^ ℓ) (ε : ℝ) (hε : 0 < ε) :
    ν.real {ω | ε < |(1 / ((η₁ : ℝ) + η₂ / 2 ^ ℓ)) *
        (∑ i ∈ Finset.univ.filter (fun i : Fin T => (i : ℕ) < η₁), X i ω +
          ∑ i ∈ Finset.univ.filter (fun i : Fin T => (i : ℕ) < η₂), Y i ω / 2 ^ ℓ) - μ|}
      ≤ 2 * Real.exp (-2 * ε ^ 2 * ((η₁ : ℝ) + η₂ / 2 ^ ℓ)) := by sorry

end FakeUserRanking.FORC
Source
Golrezaei, Manshadi, Schneider, Sekar, Learning Product Rankings Robust to Fake Users, arXiv:2009.05138v1, p. 56, Lemma 13
Human review
  • Endorsed by Shuze Chen · Oct 24, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 24, 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