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.Composite.lemma_5

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

nonconvex-optimizationp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1smooth-optimization

Let Ψ=f+h\Psi=f+hΨ=f+h as in (1.3): f:Rn→Rf:\mathbb R^n\to\mathbb Rf:Rn→R is differentiable with LfL_fLf​-Lipschitz gradient (possibly nonconvex), h:Rn→Rh:\mathbb R^n\to\mathbb Rh:Rn→R is convex and differentiable with LhL_hLh​-Lipschitz gradient, ∇Ψ=∇f+∇h\nabla\Psi=\nabla f+\nabla h∇Ψ=∇f+∇h and 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 upper bound is the usual quadratic bound for an LΨL_\PsiLΨ​-smooth function; the lower bound improves the constant from LΨL_\PsiLΨ​ to LfL_fLf​, because the convex part hhh contributes only a nonnegative term. This is what lets the analysis of Algorithm 2 depend on LfL_fLf​, and reduce to the convex rate when Lf=0L_f=0Lf​=0.

Formalization Note Smoothness is IsBetaSmooth f gf Lf (differentiable with gradient map gf, Lf ≥ 0, gradient Lf-Lipschitz), and likewise for h; Ψ\PsiΨ and ∇Ψ\nabla\Psi∇Ψ are written out as f y + h y and gf x + gh x.

Preamble
import Mathlib
import Definitions.Def_ConvexOptAlg_SmoothGD_Defs
import Definitions.Def_NonconvexAG_Composite_ProxMap
import Definitions.Def_NonconvexAG_Composite_AGRun
Formal statement
namespace NonconvexAG.Composite

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 : NonconvexAG.Smooth.E n → ℝ) (gf gh : NonconvexAG.Smooth.E n → NonconvexAG.Smooth.E n) (Lf Lh : ℝ)
    (hf : IsBetaSmooth f gf Lf) (hh : IsBetaSmooth h gh Lh) (hhc : ConvexOn ℝ Set.univ h) :
    ∀ x y : NonconvexAG.Smooth.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.Composite
Source
Ghadimi & Lan, Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming, arXiv:1310.3787v1, p. 11, Lemma 5 (2.43); the setting is (1.3), p. 2
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