Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(53) — the quadratic part of h1 at α̂ exceeds that at α∗ by at most ½ϵ² + 2ϵ

Proved
L0BnB.DualGap.ineq_53

by mikedeng1 · Oct 8, 2026 · Mathlib 0df444a (Lean v4.33.1)

dual-boundsdualityp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1sparse-regression

Let X∈Rn×pX\in\mathbb R^{n\times p}X∈Rn×p, y∈Rny\in\mathbb R^ny∈Rn with ∥y∥2=1\|y\|_2=1∥y∥2​=1, λ0,λ2,M>0\lambda_0,\lambda_2,M>0λ0​,λ2​,M>0, β∗\beta^*β∗ an optimal solution of (5) and β^∈Rp\hat\beta\in\mathbb R^pβ^​∈Rp. With α∗=−(y−Xβ∗)\alpha^*=-(y-X\beta^*)α∗=−(y−Xβ∗), α^=−(y−Xβ^)\hat\alpha=-(y-X\hat\beta)α^=−(y−Xβ^​) and ϵ=∥X(β∗−β^)∥2\epsilon=\|X(\beta^*-\hat\beta)\|_2ϵ=∥X(β∗−β^​)∥2​,

12∥α^∥22+α^⊤y≤12ϵ2+2ϵ+12∥α∗∥22+α∗⊤y.(53)\tfrac12\|\hat\alpha\|_2^2+\hat\alpha^\top y\le\tfrac12\epsilon^2+2\epsilon+\tfrac12\|\alpha^*\|_2^2+\alpha^{*\top}y.\qquad(53)21​∥α^∥22​+α^⊤y≤21​ϵ2+2ϵ+21​∥α∗∥22​+α∗⊤y.(53)

This compares the smooth part of the dual objective h1h_1h1​ at the constructed and the optimal dual points; together with Lemma 2 it gives the dual-bound guarantee.

Formalization Note The inequality holds for every β^\hat\betaβ^​; the paper applies it to the output of Algorithm 2, and no property of that output is used. It also does not depend on the regime of λ0/λ2\sqrt{\lambda_0/\lambda_2}λ0​/λ2​​ versus MMM.

Preamble
import Mathlib
import Definitions.Def_L0BnB_DualGap_Setup
import Definitions.Def_L0BnB_DualGap_Duals
Formal statement
namespace L0BnB.DualGap

/-- (53), Proof of Theorem 3, p. 33: with `‖y‖₂ = 1`, `β*` optimal for (5), `α* = −r*`, `α̂ = −r̂`
and `ϵ = ‖X(β* − β̂)‖₂`: `½‖α̂‖₂² + α̂ᵀy ≤ ½ϵ² + 2ϵ + ½‖α*‖₂² + α*ᵀy`. -/
theorem ineq_53 {n p : ℕ} (X : Matrix (Fin n) (Fin p) ℝ) (y : Fin n → ℝ)
    (lam0 lam2 M : ℝ) (hlam0 : 0 < lam0) (hlam2 : 0 < lam2) (hM : 0 < M)
    (hy : ∑ r, y r ^ 2 = 1) (βs : Fin p → ℝ) (hβs : IsOptimal X y lam0 lam2 M βs)
    (βhat : Fin p → ℝ) :
    (1 / 2) * ∑ r, alphaHat X y βhat r ^ 2 + ∑ r, alphaHat X y βhat r * y r ≤
      (1 / 2) * primalGap X βs βhat ^ 2 + 2 * primalGap X βs βhat
        + (1 / 2) * ∑ r, L0BnB.Duality.alphaStar X y βs r ^ 2 + ∑ r, L0BnB.Duality.alphaStar X y βs r * y r := by sorry

end L0BnB.DualGap
Source
Hazimeh, Mazumder, Saab, Sparse Regression at Scale: Branch-and-Bound rooted in First-Order Optimization, arXiv:2004.06152v2, p. 33, Proof of Theorem 3, (53) (from (52), p. 32)
Human review
  • Endorsed by Shuze Chen · Oct 8, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 8, 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