Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eq. (10) — the sub-gradient inequality for λ-strongly convex functions

Proved
Pegasos.Analysis.eq_10

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

p2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1strong-convexitysubgradient

Call f:Rn→Rf:\mathbb R^n\to\mathbb Rf:Rn→R λ\lambdaλ-strongly convex if w↦f(w)−λ2∥w∥2w \mapsto f(w) - \frac\lambda2\|w\|^2w↦f(w)−2λ​∥w∥2 is convex, and call ggg a sub-gradient of fff at www if f(u)−f(w)≥⟨g,u−w⟩f(u) - f(w) \ge \langle g, u - w\ranglef(u)−f(w)≥⟨g,u−w⟩ for every uuu.

If fff is λ\lambdaλ-strongly convex and ggg is a sub-gradient of fff at www, then for every u∈Rnu \in \mathbb R^nu∈Rn

⟨w−u,g⟩  ≥  f(w)−f(u)+λ2∥w−u∥2.\langle w - u, g\rangle \;\ge\; f(w) - f(u) + \frac{\lambda}{2}\|w - u\|^2 .⟨w−u,g⟩≥f(w)−f(u)+2λ​∥w−u∥2.

This is the per-round inequality that, in the proof of Lemma 1, upgrades the linear lower bound of a sub-gradient to a quadratic one; it is what produces the logarithmic rate.

Formalization Note. Strong convexity is stated as the paper defines it (p. 9), as convexity of f−λ2∥⋅∥2f - \frac\lambda2\|\cdot\|^2f−2λ​∥⋅∥2 on all of Rn\mathbb R^nRn; no sign condition on λ\lambdaλ is imposed, since the inequality holds for every real λ\lambdaλ. No differentiability is assumed.

Preamble
import Mathlib
import Definitions.Def_Pegasos_Analysis_Model
Formal statement
namespace Pegasos.Analysis

/-- **Eq. (10)** (p. 10, proof of Lemma 1): if `f` is λ-strongly convex in the paper's sense
(`f(w) − λ/2‖w‖²` is convex, p. 9) and `g` is a sub-gradient of `f` at `w`
(`∀ u, f(u) − f(w) ≥ ⟨g, u − w⟩`, p. 17), then for every `u`,
`⟨w − u, g⟩ ≥ f(w) − f(u) + λ/2 ‖w − u‖²`. -/
theorem eq_10 {n : ℕ} (lam : ℝ) (f : EuclideanSpace ℝ (Fin n) → ℝ)
    (hf : ConvexOn ℝ Set.univ (fun v => f v - lam / 2 * ‖v‖ ^ 2))
    (w g : EuclideanSpace ℝ (Fin n)) (hg : UnderstandingML.IsSubgradient f w g)
    (u : EuclideanSpace ℝ (Fin n)) :
    f w - f u + lam / 2 * ‖w - u‖ ^ 2 ≤ inner ℝ (w - u) g := by sorry

end Pegasos.Analysis
Source
Shalev-Shwartz, Singer, Srebro & Cotter, Pegasos: primal estimated sub-gradient solver for SVM, Math. Program. 127 (2011), p. 10, Eq. (10) (proof of Lemma 1); λ-strong convexity p. 9; sub-gradient p. 17
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