Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Derivation of Result 4, p. 353 — first and second derivatives of E(e^{−y(F(x)+f(x))}|x) at f(x) = 0

Proved
AddLogReg.Gentle.derivation_derivs

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

boostingexponential-lossgentle-adaboostnewton-methodp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let ν\nuν be a probability measure on X×{−1,1}X\times\{-1,1\}X×{−1,1}, the joint law of (x,y)(x,y)(x,y), let F:X→RF : X\to\mathbb RF:X→R and fix x∈Xx\in Xx∈X. Write J(F(x)+f(x))=E(e−y(F(x)+f(x))∣x)J(F(x)+f(x)) = E\big(e^{-y(F(x)+f(x))}\mid x\big)J(F(x)+f(x))=E(e−y(F(x)+f(x))∣x), a function of the real number f(x)f(x)f(x). Then

  1. JJJ is differentiable at f(x)=0f(x) = 0f(x)=0 with
∂J(F(x)+f(x))∂f(x)∣f(x)=0=−E(e−yF(x)y∣x);\frac{\partial J(F(x)+f(x))}{\partial f(x)}\bigg|_{f(x)=0} = -E\big(e^{-yF(x)}y\mid x\big);∂f(x)∂J(F(x)+f(x))​​f(x)=0​=−E(e−yF(x)y∣x);
  1. at every f(x)=tf(x) = tf(x)=t the derivative is −E(e−y(F(x)+t)y∣x)-E\big(e^{-y(F(x)+t)}y\mid x\big)−E(e−y(F(x)+t)y∣x);
  2. this first derivative is itself differentiable at 000, with
∂2J(F(x)+f(x))∂f(x)2∣f(x)=0=E(e−yF(x)y2∣x)=E(e−yF(x)∣x),\frac{\partial^2 J(F(x)+f(x))}{\partial f(x)^2}\bigg|_{f(x)=0} = E\big(e^{-yF(x)}y^2\mid x\big) = E\big(e^{-yF(x)}\mid x\big),∂f(x)2∂2J(F(x)+f(x))​​f(x)=0​=E(e−yF(x)y2∣x)=E(e−yF(x)∣x),

the last equality because y2=1y^2 = 1y2=1.

These are the gradient and Hessian that the Newton step of Result 4 is built from.

Formalization Note Derivatives are stated with HasDerivAt, so differentiability is part of the claim. The second derivative is the derivative at 000 of the explicit function t↦−E(e−y(F(x)+t)y∣x)t\mapsto -E(e^{-y(F(x)+t)}y\mid x)t↦−E(e−y(F(x)+t)y∣x), which conjunct 2 shows to be the derivative of JJJ at every ttt. The statement holds for every xxx (conditional expectations are integrals against the conditional law ν.condKernel x on the two-point label set).

Preamble
import Mathlib
import Definitions.Def_AddLogReg_Gentle_Setting

open MeasureTheory ProbabilityTheory
Formal statement
namespace AddLogReg.Gentle

theorem derivation_derivs {X : Type*} [MeasurableSpace X] (ν : Measure (X × Bool))
    [IsProbabilityMeasure ν] (F : X → ℝ) (x : X) :
    HasDerivAt (condCritAt ν F x)
        (-∫ b, Real.exp (-(AddLogReg.ExpCrit.sgn b * F x)) * AddLogReg.ExpCrit.sgn b ∂(ν.condKernel x)) 0 ∧
      (∀ t : ℝ, HasDerivAt (condCritAt ν F x)
        (-∫ b, Real.exp (-(AddLogReg.ExpCrit.sgn b * (F x + t))) * AddLogReg.ExpCrit.sgn b ∂(ν.condKernel x)) t) ∧
      HasDerivAt (fun t : ℝ => -∫ b, Real.exp (-(AddLogReg.ExpCrit.sgn b * (F x + t))) * AddLogReg.ExpCrit.sgn b ∂(ν.condKernel x))
        (∫ b, Real.exp (-(AddLogReg.ExpCrit.sgn b * F x)) * AddLogReg.ExpCrit.sgn b ^ 2 ∂(ν.condKernel x)) 0 ∧
      ∫ b, Real.exp (-(AddLogReg.ExpCrit.sgn b * F x)) * AddLogReg.ExpCrit.sgn b ^ 2 ∂(ν.condKernel x) =
        ∫ b, Real.exp (-(AddLogReg.ExpCrit.sgn b * F x)) ∂(ν.condKernel x) := by sorry

end AddLogReg.Gentle
Source
Friedman, Hastie and Tibshirani, Additive logistic regression: a statistical view of boosting, Ann. Statist. 28 (2000), p. 353, §4.4, Derivation of Result 4, first and second displays
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