Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(2.47) — the L_f-corrected convexity gap at x^md_k

Proved
NonconvexAG.Composite.eq_2_47

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

accelerated-gradientcomposite-optimizationnonconvex-optimizationp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1

Let Ψ=f+h\Psi=f+hΨ=f+h be as in (1.3) and Lemma 5 (fff LfL_fLf​-smooth, hhh convex and LhL_hLh​-smooth, ∇Ψ=∇f+∇h\nabla\Psi=\nabla f+\nabla h∇Ψ=∇f+∇h), and run Algorithm 2 with step sizes satisfying α1=1\alpha_1=1α1​=1, αk∈(0,1)\alpha_k\in(0,1)αk​∈(0,1) (k≥2k\ge2k≥2), βk,λk>0\beta_k,\lambda_k>0βk​,λk​>0, any prox map and any starting point x0x_0x0​. Then for every k≥1k\ge1k≥1 and every x∈Rnx\in\mathbb R^nx∈Rn,

Ψ(xkmd)−[(1−αk)Ψ(xk−1ag)+αkΨ(x)]≤⟨∇Ψ(xkmd), xkmd−αkx−(1−αk)xk−1ag⟩+Lfαk2∥xkmd−x∥2+Lfαk2(1−αk)2∥xk−1ag−xk−1∥2.\Psi(x^{md}_k)-\big[(1-\alpha_k)\Psi(x^{ag}_{k-1})+\alpha_k\Psi(x)\big]\le\big\langle\nabla\Psi(x^{md}_k),\,x^{md}_k-\alpha_kx-(1-\alpha_k)x^{ag}_{k-1}\big\rangle+\frac{L_f\alpha_k}2\|x^{md}_k-x\|^2+\frac{L_f\alpha_k^2(1-\alpha_k)}2\|x^{ag}_{k-1}-x_{k-1}\|^2 .Ψ(xkmd​)−[(1−αk​)Ψ(xk−1ag​)+αk​Ψ(x)]≤⟨∇Ψ(xkmd​),xkmd​−αk​x−(1−αk​)xk−1ag​⟩+2Lf​αk​​∥xkmd​−x∥2+2Lf​αk2​(1−αk​)​∥xk−1ag​−xk−1​∥2.

For convex Ψ\PsiΨ (the case Lf=0L_f=0Lf​=0) this is the familiar convexity step of accelerated methods; the two LfL_fLf​-terms measure the price of nonconvexity of fff.

Formalization Note Only the outer ends of the printed chain are stated. The prox map plays no role here beyond defining the iterates.

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

/-- (2.47), p. 12 (outer ends of the chain), for Algorithm 2 on `Ψ = f + h`, every `k ≥ 1` and
every `x ∈ ℝⁿ`. -/
theorem eq_2_47 {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)
    (P : NonconvexAG.Smooth.E n → NonconvexAG.Smooth.E n → ℝ → NonconvexAG.Smooth.E n) (α β lam : ℕ → ℝ) (hstep : NonconvexAG.Smooth.AGStepsizes α β lam) (x0 : NonconvexAG.Smooth.E n) :
    let Ψ : NonconvexAG.Smooth.E n → ℝ := fun x => f x + h x
    let gΨ : NonconvexAG.Smooth.E n → NonconvexAG.Smooth.E n := fun x => gf x + gh x
    let xk : ℕ → NonconvexAG.Smooth.E n := xSeq gΨ P α β lam x0
    let xag : ℕ → NonconvexAG.Smooth.E n := xagSeq gΨ P α β lam x0
    let xmd : ℕ → NonconvexAG.Smooth.E n := xmdSeq gΨ P α β lam x0
    ∀ k, 1 ≤ k → ∀ x : NonconvexAG.Smooth.E n,
      Ψ (xmd k) - ((1 - α k) * Ψ (xag (k - 1)) + α k * Ψ x) ≤
        inner ℝ (gΨ (xmd k)) (xmd k - α k • x - (1 - α k) • xag (k - 1)) +
          Lf * α k / 2 * ‖xmd k - x‖ ^ 2 +
          Lf * α k ^ 2 * (1 - α k) / 2 * ‖xag (k - 1) - xk (k - 1)‖ ^ 2 := by sorry
end NonconvexAG.Composite
Source
Ghadimi & Lan, Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming, arXiv:1310.3787v1, p. 12, (2.47)
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