Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§4.1, p. 345, proof of Lemma 1 — E(e^{−yF(x)}|x) = P(y=1|x)e^{−F(x)} + P(y=−1|x)e^{F(x)}, and J(F) = E_x[E(e^{−yF(x)}|x)]

Proved
AddLogReg.ExpCrit.cond_criterion

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

boostingconditional-expectationexponential-lossp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let ν\nuν be the joint law of (x,y)(x, y)(x,y) on X×{−1,1}X \times \{-1, 1\}X×{−1,1}, with marginal νX\nu_XνX​ on XXX, and let P(y=±1∣x)P(y = \pm 1 \mid x)P(y=±1∣x) be the conditional class probabilities. Then:

  1. for every x∈Xx \in Xx∈X and every real ttt, the conditional exponential criterion at F(x)=tF(x) = tF(x)=t is
E(e−yt∣x)=P(y=1∣x) e−t+P(y=−1∣x) et;E\big(e^{-yt} \mid x\big) = P(y = 1 \mid x)\, e^{-t} + P(y = -1 \mid x)\, e^{t};E(e−yt∣x)=P(y=1∣x)e−t+P(y=−1∣x)et;
  1. for every measurable F:X→RF : X \to \mathbb RF:X→R, the exponential criterion J(F)=E(e−yF(x))J(F) = E(e^{-yF(x)})J(F)=E(e−yF(x)) is the νX\nu_XνX​-expectation of the conditional criterion:
J(F)=∫XE(e−yF(x)∣x) dνX(x).J(F) = \int_X E\big(e^{-yF(x)} \mid x\big)\, d\nu_X(x).J(F)=∫X​E(e−yF(x)∣x)dνX​(x).

This is the first display of the proof of Lemma 1, together with the reduction "it is sufficient to minimize the criterion conditional on xxx": the joint minimization of JJJ splits into one scalar minimization for each xxx.

Formalization Note Both sides of item 2 are lower Lebesgue integrals in [0,∞][0, \infty][0,∞]; the conditional criterion is a finite nonnegative real converted with ENNReal.ofReal. Item 1 holds at every xxx, since the conditional kernel is a probability measure at every point.

Preamble
import Mathlib
import Definitions.Def_AddLogReg_ExpCrit_Setting

open MeasureTheory ProbabilityTheory
Formal statement
namespace AddLogReg.ExpCrit

/-- Proof of Lemma 1, first display (p. 345): `E(e^{−yF(x)}|x) = P(y = 1|x)e^{−F(x)} +
P(y = −1|x)e^{F(x)}`, and the joint criterion is the expectation over `x` of the conditional one. -/
theorem cond_criterion {X : Type*} [MeasurableSpace X] (ν : Measure (X × Bool))
    [IsProbabilityMeasure ν] :
    (∀ (x : X) (t : ℝ),
      condCrit ν x t = condProb ν true x * Real.exp (-t) + condProb ν false x * Real.exp t) ∧
    (∀ F : X → ℝ, Measurable F →
      J ν F = ∫⁻ x, ENNReal.ofReal (condCrit ν x (F x)) ∂ν.fst) := by sorry

end AddLogReg.ExpCrit
Source
Friedman, Hastie and Tibshirani, Additive logistic regression: a statistical view of boosting, Ann. Statist. 28 (2000), p. 345, §4.1, proof of Lemma 1, first display
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