Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 5 — −(L_f/2)‖y − x‖² ≤ Ψ(y) − Ψ(x) − ⟨∇Ψ(x), y − x⟩ ≤ (L_Ψ/2)‖y − x‖²

Proved
NonconvexAG.StochComposite.lemma_5

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

composite-optimizationnonconvex-optimizationp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1

Let Ψ=f+h\Psi=f+hΨ=f+h, where f:Rn→Rf:\mathbb R^n\to\mathbb Rf:Rn→R is differentiable with LfL_fLf​-Lipschitz gradient (possibly nonconvex) and h:Rn→Rh:\mathbb R^n\to\mathbb Rh:Rn→R is convex and differentiable with LhL_hLh​-Lipschitz gradient, and let LΨ=Lf+LhL_\Psi=L_f+L_hLΨ​=Lf​+Lh​. Then for all x,y∈Rnx,y\in\mathbb R^nx,y∈Rn

−Lf2∥y−x∥2≤Ψ(y)−Ψ(x)−⟨∇Ψ(x),y−x⟩≤LΨ2∥y−x∥2.-\frac{L_f}2\|y-x\|^2\le\Psi(y)-\Psi(x)-\langle\nabla\Psi(x),y-x\rangle\le\frac{L_\Psi}2\|y-x\|^2.−2Lf​​∥y−x∥2≤Ψ(y)−Ψ(x)−⟨∇Ψ(x),y−x⟩≤2LΨ​​∥y−x∥2.

The lower bound measures how far Ψ\PsiΨ is from convex in terms of LfL_fLf​ alone; it is what makes the final bound of Theorem 4 depend on LfL_fLf​ rather than on LΨL_\PsiLΨ​ in its non-convexity term.

Formalization Note ∇Ψ=∇f+∇h\nabla\Psi=\nabla f+\nabla h∇Ψ=∇f+∇h is written out. Restated from mission 2 of this series because drafts cannot import one another.

Preamble
import Mathlib
import Definitions.Def_ConvexOptAlg_SmoothGD_Defs
import Definitions.Def_GhadimiLan_RSG_Model
import Definitions.Def_NonconvexAG_StochComposite_ProxMap
import Definitions.Def_NonconvexAG_StochComposite_RSAG
open MeasureTheory ProbabilityTheory
open scoped InnerProductSpace
Formal statement
namespace NonconvexAG.StochComposite

open GhadimiLan.RSG (E)
open ConvexOptAlg.SmoothGD

/-- Lemma 5 (p. 11), (2.43): `Ψ = f + h` with `f ∈ C^{1,1}_{L_f}`, `h ∈ C^{1,1}_{L_h}` convex,
`∇Ψ = ∇f + ∇h` and `L_Ψ = L_f + L_h`. -/
theorem lemma_5 {n : ℕ} (f h : E n → ℝ) (gf gh : E n → E n) (Lf Lh : ℝ)
    (hf : IsBetaSmooth f gf Lf) (hh : IsBetaSmooth h gh Lh) (hhc : ConvexOn ℝ Set.univ h) :
    ∀ x y : E n,
      -(Lf / 2) * ‖y - x‖ ^ 2 ≤ (f y + h y) - (f x + h x) - inner ℝ (gf x + gh x) (y - x) ∧
        (f y + h y) - (f x + h x) - inner ℝ (gf x + gh x) (y - x) ≤
          (Lf + Lh) / 2 * ‖y - x‖ ^ 2 := by sorry

end NonconvexAG.StochComposite
Source
Ghadimi & Lan, Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming, arXiv:1310.3787v1, p. 11, Lemma 5, (2.43)
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