Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 2, p. 30 — the outer minimisation over λ for logistic regression

Proved
RWPI.Classif.logistic_outer_min

by mikedeng1 · Oct 5, 2026 · Mathlib 0df444a (Lean v4.33.1)

distributionally-robust-optimizationdualitylogistic-regressionp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1

Let p,q∈[1,∞]p, q \in [1,\infty]p,q∈[1,∞] satisfy 1/p+1/q=11/p + 1/q = 11/p+1/q=1. Let (X1,Y1),…,(Xn,Yn)∈Rd×{−1,+1}(X_1,Y_1),\dots,(X_n,Y_n) \in \mathbb R^d \times \{-1,+1\}(X1​,Y1​),…,(Xn​,Yn​)∈Rd×{−1,+1} with n≥1n \ge 1n≥1, let β∈Rd\beta \in \mathbb R^dβ∈Rd and δ≥0\delta \ge 0δ≥0. Then

inf⁡λ≥0{δλ+1n∑i=1nsup⁡x∈Rd{log⁡(1+exp⁡(−YiβTx))−λ∥x−Xi∥q}}=1n∑i=1nlog⁡(1+exp⁡(−YiβTXi))+δ ∥β∥p.\inf_{\lambda \ge 0}\Big\{ \delta\lambda + \frac1n\sum_{i=1}^n \sup_{x\in\mathbb R^d}\Big\{ \log\big(1+\exp(-Y_i\beta^T x)\big) - \lambda\|x - X_i\|_q \Big\}\Big\} = \frac1n\sum_{i=1}^n \log\big(1+\exp(-Y_i\beta^T X_i)\big) + \delta\,\|\beta\|_p .λ≥0inf​{δλ+n1​i=1∑n​x∈Rdsup​{log(1+exp(−Yi​βTx))−λ∥x−Xi​∥q​}}=n1​i=1∑n​log(1+exp(−Yi​βTXi​))+δ∥β∥p​.

Combined with Proposition 1, the left-hand side is the worst-case expected logistic loss over the ball {P:DNq(P,Pn)≤δ}\{P : D_{N_q}(P,P_n)\le\delta\}{P:DNq​​(P,Pn​)≤δ}; the identity is therefore the per-β\betaβ form of the logistic half of Theorem 2.

Formalization Note The paper's chain passes through indicators printed as 1{λ>∥β∥}\mathbf 1_{\{\lambda > \|\beta\|\}}1{λ>∥β∥}​ and ∞ 1{λ≤∥β∥}\infty\,\mathbf 1_{\{\lambda \le \|\beta\|\}}∞1{λ≤∥β∥}​; by the previous step the inner supremum is finite at λ=∥β∥\lambda = \|\beta\|λ=∥β∥, so the correct indicators are 1{λ≥∥β∥}\mathbf 1_{\{\lambda \ge \|\beta\|\}}1{λ≥∥β∥}​ and ∞ 1{λ<∥β∥}\infty\,\mathbf 1_{\{\lambda < \|\beta\|\}}∞1{λ<∥β∥}​. The statement here is the first member of the chain equal to its last member, which is unaffected. Norms are in Theorem 2's convention (the page swaps ppp and qqq). Values are in [0,∞][0,\infty][0,∞].

Preamble
import Mathlib
import Definitions.Def_RWPI_Classif_losses

open scoped ENNReal
Formal statement
namespace RWPI.Classif

/-- App. A.1, proof of Theorem 2, p. 30 (the chain after the inner supremum): for labels
`Yᵢ ∈ {−1, +1}` and `δ ≥ 0`,
`inf_{λ ≥ 0} { δλ + (1/n) Σᵢ sup_x { log(1 + exp(−Yᵢβᵀx)) − λ‖x − Xᵢ‖_q } }
  = (1/n) Σᵢ log(1 + exp(−Yᵢβᵀ Xᵢ)) + δ‖β‖_p`. -/
theorem logistic_outer_min {d n : ℕ} (hn : 0 < n) (X : Fin n → Fin d → ℝ) (Y : Fin n → ℝ)
    (hY : ∀ i, Y i = 1 ∨ Y i = -1) (p q : ℝ≥0∞) (hpq : p.HolderConjugate q)
    (β : Fin d → ℝ) (δ : ℝ) (hδ : 0 ≤ δ) :
    (⨅ (lam : ℝ) (_ : 0 ≤ lam), (ENNReal.ofReal (δ * lam) + (n : ℝ≥0∞)⁻¹ *
        ∑ i, ⨆ x : Fin d → ℝ, (ENNReal.ofReal (logLoss β (x, Y i)) -
          ENNReal.ofReal lam * ENNReal.ofReal ‖WithLp.toLp q (x - X i)‖))) =
      ENNReal.ofReal ((1 / (n : ℝ)) * ∑ i, logLoss β (X i, Y i) + δ * ‖WithLp.toLp p β‖) := by sorry

end RWPI.Classif
Source
Blanchet, Kang & Murthy, Robust Wasserstein Profile Inference and Applications to Machine Learning, arXiv:1610.05627v4, App. A.1, proof of Theorem 2, p. 30 (third display)
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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