Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(34)–(35), p. 352 — F(x) − H(x)⁻¹s(x) = F(x) + ½E(y*−p|x)/E(p(1−p)|x) = F(x) + ½E_w((y*−p)/(p(1−p))|x)

Proved
AddLogReg.LogitBoost.eq_34_35

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

boostinglogistic-regressionlogitboostnewton-methodp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let ν\nuν be a probability measure on X×{0,1}X\times\{0,1\}X×{0,1}, F:X→RF : X\to\mathbb RF:X→R, p(x)=eF(x)/(eF(x)+e−F(x))p(x) = e^{F(x)}/(e^{F(x)}+e^{-F(x)})p(x)=eF(x)/(eF(x)+e−F(x)), and let

s(x)=2E(y∗−p(x)∣x),H(x)=−4E(p(x)(1−p(x))∣x)s(x) = 2E\big(y^*-p(x)\mid x\big),\qquad H(x) = -4E\big(p(x)(1-p(x))\mid x\big)s(x)=2E(y∗−p(x)∣x),H(x)=−4E(p(x)(1−p(x))∣x)

be the score (32) and Hessian (33). Then H(x)≠0H(x)\neq 0H(x)=0, and the Newton update satisfies

F(x)−H(x)−1s(x)=F(x)+12 E(y∗−p(x)∣x)E(p(x)(1−p(x))∣x)=F(x)+12Ew ⁣(y∗−p(x)p(x)(1−p(x)) ∣ x),F(x) - H(x)^{-1}s(x) = F(x) + \frac12\,\frac{E(y^*-p(x)\mid x)}{E(p(x)(1-p(x))\mid x)} = F(x) + \frac12 E_w\!\left(\frac{y^*-p(x)}{p(x)(1-p(x))}\ \Big|\ x\right),F(x)−H(x)−1s(x)=F(x)+21​E(p(x)(1−p(x))∣x)E(y∗−p(x)∣x)​=F(x)+21​Ew​(p(x)(1−p(x))y∗−p(x)​ ​ x),

where EwE_wEw​ is the weighted conditional expectation with weight w(x)=p(x)(1−p(x))w(x) = p(x)(1-p(x))w(x)=p(x)(1−p(x)).

The last expression is F(x)F(x)F(x) plus one half of the population weighted least-squares fit of the working response zzz of Algorithm 3, which is what identifies LogitBoost's step with a Newton step.

Formalization Note H(x)≠0H(x)\neq0H(x)=0 is part of the conclusion, not a hypothesis: it holds because 0<p(x)<10<p(x)<10<p(x)<1. Without it the Lean division s/Hs/Hs/H would silently return 000.

Preamble
import Mathlib
import Definitions.Def_AddLogReg_LogitBoost_Setting

open MeasureTheory ProbabilityTheory
Formal statement
namespace AddLogReg.LogitBoost

theorem eq_34_35 {X : Type*} [MeasurableSpace X] (ν : Measure (X × Bool))
    [IsProbabilityMeasure ν] (F : X → ℝ) (x : X) :
    (-4 * ∫ _b, symLogistic (F x) * (1 - symLogistic (F x)) ∂(ν.condKernel x) ≠ 0) ∧
      F x - (2 * ∫ b, (ystar b - symLogistic (F x)) ∂(ν.condKernel x)) /
          (-4 * ∫ _b, symLogistic (F x) * (1 - symLogistic (F x)) ∂(ν.condKernel x)) =
        F x + (1 / 2) * ((∫ b, (ystar b - symLogistic (F x)) ∂(ν.condKernel x)) /
          ∫ _b, symLogistic (F x) * (1 - symLogistic (F x)) ∂(ν.condKernel x)) ∧
      F x + (1 / 2) * ((∫ b, (ystar b - symLogistic (F x)) ∂(ν.condKernel x)) /
          ∫ _b, symLogistic (F x) * (1 - symLogistic (F x)) ∂(ν.condKernel x)) =
        F x + (1 / 2) * wCondExpBy ν (logitWeight F) (workingResponse F) x := by sorry

end AddLogReg.LogitBoost
Source
Friedman, Hastie and Tibshirani, Additive logistic regression: a statistical view of boosting, Ann. Statist. 28 (2000), p. 352, (34)–(35)
Human review
  • Endorsed by Shuze Chen · Oct 7, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 7, 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