Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 2, p. 31 — the outer minimisation over λ for the hinge-loss SVM

Proved
RWPI.Classif.hinge_outer_min

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

distributionally-robust-optimizationdualityp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1support-vector-machine

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

The paper observes that it suffices to restrict the outer minimization to λ≥∥β∥p\lambda \ge \|\beta\|_pλ≥∥β∥p​ (elsewhere the inner suprema are infinite) and evaluates the restricted infimum; the statement combines the two. With Proposition 1 the left-hand side is the worst-case expected hinge loss over {P:DNq(P,Pn)≤δ}\{P : D_{N_q}(P,P_n)\le\delta\}{P:DNq​​(P,Pn​)≤δ}, so this is the per-β\betaβ form of the SVM half of Theorem 2.

Formalization Note Norms are in Theorem 2's convention (the page writes the threshold as ∥β∥q\|\beta\|_q∥β∥q​). 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. 31: for labels `Yᵢ ∈ {−1, +1}` and `δ ≥ 0`, the outer
minimisation of the dual over `λ ≥ 0` (where it suffices to take `λ ≥ ‖β‖_p`) gives
`inf_{λ ≥ 0} { δλ + (1/n) Σᵢ sup_Δ { (1 − Yᵢβᵀ(Xᵢ + Δ))⁺ − λ‖Δ‖_q } }
  = (1/n) Σᵢ (1 − Yᵢβᵀ Xᵢ)⁺ + δ‖β‖_p`. -/
theorem hinge_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, ⨆ Δ : Fin d → ℝ, (ENNReal.ofReal (hingeLoss β (X i + Δ, Y i)) -
          ENNReal.ofReal lam * ENNReal.ofReal ‖WithLp.toLp q Δ‖))) =
      ENNReal.ofReal ((1 / (n : ℝ)) * ∑ i, hingeLoss 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. 31 (display after 'it is sufficient to restrict to λ ≥ ‖β‖')
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