Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Definition 1, p. 354 — the symmetric multiple logistic transformation (39) is equivalent to (40) with Σ F_k = 0

Proved
AddLogReg.Multiclass.def_1_equiv

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

multiclass-classificationmultinomial-logistic-regressionp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1softmax

Let J≥1J\ge1J≥1 and let p=(p1,…,pJ)p=(p_1,\dots,p_J)p=(p1​,…,pJ​) be a probability vector with all entries positive: pj>0p_j>0pj​>0 and ∑jpj=1\sum_j p_j = 1∑j​pj​=1. For any real vector F=(F1,…,FJ)F=(F_1,\dots,F_J)F=(F1​,…,FJ​) the following are equivalent:

  1. FFF is the symmetric multiple logistic transformation (39) of ppp:
Fj=log⁡pj−1J∑k=1Jlog⁡pk(j=1,…,J);F_j = \log p_j - \frac1J\sum_{k=1}^J\log p_k\qquad(j=1,\dots,J);Fj​=logpj​−J1​k=1∑J​logpk​(j=1,…,J);
  1. FFF satisfies (40):
pj=eFj∑k=1JeFk(j=1,…,J),∑k=1JFk=0.p_j = \frac{e^{F_j}}{\sum_{k=1}^J e^{F_k}}\quad(j=1,\dots,J),\qquad \sum_{k=1}^J F_k = 0 .pj​=∑k=1J​eFk​eFj​​(j=1,…,J),k=1∑J​Fk​=0.

This is the equivalence of the two forms of Definition 1. It says that (39) is the unique centred inverse of the softmax map (40), and is what lets the multiclass LogitBoost algorithm work on the centred scores FjF_jFj​ and recover probabilities through (40).

Formalization Note The positivity of every pjp_jpj​ is what "pj(x)=P(yj=1∣x)p_j(x) = P(y_j = 1\mid x)pj​(x)=P(yj​=1∣x)" with log⁡pj\log p_jlogpj​ defined requires: Lean's Real.log 0 = 0 would otherwise give (39) a junk value. The vector form is the statement at a fixed xxx.

Preamble
import Mathlib
import Definitions.Def_AddLogReg_Multiclass_Setting

open MeasureTheory ProbabilityTheory ENNReal
Formal statement
namespace AddLogReg.Multiclass

theorem def_1_equiv {J : ℕ} [NeZero J] (p : Fin J → ℝ) (hp_pos : ∀ j, 0 < p j)
    (hp_sum : ∑ j, p j = 1) (F : Fin J → ℝ) :
    F = symMultiLogit p ↔ ((∀ j, p j = softmax F j) ∧ ∑ k, F k = 0) := by sorry

end AddLogReg.Multiclass
Source
Friedman, Hastie and Tibshirani, Additive logistic regression: a statistical view of boosting, Ann. Statist. 28 (2000), p. 354, Definition 1, (39)–(40) and the sentence after (40)
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