Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 1, p. 6 — quasi-strong convexity (10) implies quadratic under-approximation (13) with the same κ

Proved
NecoaraNG.Chain.theorem_1

by mikedeng1 · Oct 9, 2026 · Mathlib 0df444a (Lean v4.33.1)

p2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1quadratic-growthquasi-strong-convexity

Let X⊆RnX\subseteq\mathbb R^nX⊆Rn be closed and convex, let fff be convex on XXX, differentiable at every point of XXX, with LfL_fLf​-Lipschitz gradient on XXX (Lf>0L_f>0Lf​>0), and assume the optimal set X∗=arg⁡min⁡x∈Xf(x)X^*=\arg\min_{x\in X}f(x)X∗=argminx∈X​f(x) is nonempty. Let κ>0\kappa>0κ>0, and write xˉ=[x]X∗\bar x=[x]_{X^*}xˉ=[x]X∗​ for a nearest point of X∗X^*X∗ to xxx and f∗f^*f∗ for the optimal value. If

f∗≥f(x)+⟨∇f(x),xˉ−x⟩+κ2∥x−xˉ∥2∀x∈X,f^*\ge f(x)+\langle\nabla f(x),\bar x-x\rangle+\frac{\kappa}{2}\|x-\bar x\|^2\qquad\forall x\in X,f∗≥f(x)+⟨∇f(x),xˉ−x⟩+2κ​∥x−xˉ∥2∀x∈X,

then

f(x)≥f∗+⟨∇f(xˉ),x−xˉ⟩+κ2∥x−xˉ∥2∀x∈X.f(x)\ge f^*+\langle\nabla f(\bar x),x-\bar x\rangle+\frac{\kappa}{2}\|x-\bar x\|^2\qquad\forall x\in X.f(x)≥f∗+⟨∇f(xˉ),x−xˉ⟩+2κ​∥x−xˉ∥2∀x∈X.

In class notation: qSLf,κ(X)⊆ULf,κ(X)q\mathcal S_{L_f,\kappa}(X)\subseteq\mathcal U_{L_f,\kappa}(X)qSLf​,κ​(X)⊆ULf​,κ​(X) (14). Convexity of fff is essential: (10) alone does not even imply convexity.

Formalization Note f∗f^*f∗ is written f(xˉ)f(\bar x)f(xˉ); both inequalities are required for every nearest point xˉ\bar xxˉ (which is unique here).

Preamble
import Mathlib
import Definitions.Def_NecoaraNG_Chain_Setting
Formal statement
namespace NecoaraNG.Chain

open scoped InnerProductSpace

/-- Theorem 1, p. 6: inequality (10) implies inequality (13), with the same constant `κ`. -/
theorem theorem_1 {n : ℕ} (X : Set (E n)) (hXc : IsClosed X) (hXconv : Convex ℝ X)
    (f : E n → ℝ) (hf : ConvexOn ℝ X f) (hdiff : ∀ x ∈ X, DifferentiableAt ℝ f x)
    (Lf : ℝ) (hLf : 0 < Lf)
    (hL : ∀ x ∈ X, ∀ y ∈ X, ‖gradient f x - gradient f y‖ ≤ Lf * ‖x - y‖)
    (xstar : E n) (hxstar : xstar ∈ optSet X f) (κ : ℝ) (hκ : 0 < κ) :
    QuasiStrong X f κ → QuadUnder X f κ := by sorry

end NecoaraNG.Chain
Source
Necoara, Nesterov & Glineur, Linear convergence of first order methods for non-strongly convex optimization, arXiv:1504.06298v4, p. 6, Theorem 1, (14)
Human review
  • Endorsed by Shuze Chen · Oct 9, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 9, 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