Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(93), p. 22 — on a run of (91) + (73), ℒ̂_k − ℒ_k ≤ −α_kℒ̂_k + (α_k²/(2γ_k))‖∇f(y_k)‖²

Proved
NAGFlow.GradCorr.eq_93

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

accelerated-gradientlyapunov-functionode-discretizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let VVV be a real Hilbert space, f∈Sμ1f\in\mathcal S^1_\muf∈Sμ1​ with μ≥0\mu\ge0μ≥0, and let x∗x^*x∗ be a global minimiser of fff. Let (αk,γk)(\alpha_k,\gamma_k)(αk​,γk​) satisfy (73) with γ0>0\gamma_0>0γ0​>0 and step sizes αk>0\alpha_k>0αk​>0, and let (xk,yk,vk)(x_k,y_k,v_k)(xk​,yk​,vk​) be a run of the corrected scheme (91) for some constant LLL. With Lk=f(xk)−f(x∗)+γk2∥vk−x∗∥2\mathcal L_k=f(x_k)-f(x^*)+\frac{\gamma_k}{2}\|v_k-x^*\|^2Lk​=f(xk​)−f(x∗)+2γk​​∥vk​−x∗∥2 (74) and

L^k=f(yk)−f(x∗)+γk+12∥vk+1−x∗∥2(84),\widehat{\mathcal L}_k=f(y_k)-f(x^*)+\frac{\gamma_{k+1}}{2}\|v_{k+1}-x^*\|^2\qquad(84),Lk​=f(yk​)−f(x∗)+2γk+1​​∥vk+1​−x∗∥2(84),

for every kkk,

L^k−Lk≤−αkL^k+αk22γk∥∇f(yk)∥2.(93)\widehat{\mathcal L}_k-\mathcal L_k\le-\alpha_k\widehat{\mathcal L}_k+\frac{\alpha_k^2}{2\gamma_k}\|\nabla f(y_k)\|^2.\qquad(93)Lk​−Lk​≤−αk​Lk​+2γk​αk2​​∥∇f(yk​)∥2.(93)

This is (82) of Lemma 5.1 for the first two lines of (91), which form a Gauss–Seidel step (80) with yky_kyk​ in place of xk+1x_{k+1}xk+1​. It is the first step of the proof of Theorem 5.2.

Formalization Note. Only the first two lines of (91) and (73) are used; the correction step and the value of LLL play no role, and only f∈Sμ1f\in\mathcal S^1_\muf∈Sμ1​ is assumed. No step-size rule is assumed. ∥⋅∥∗\|\cdot\|_*∥⋅∥∗​ is the norm of VVV (Riesz).

Preamble
import Mathlib
import Definitions.Def_NAGFlow_GradCorr_Setting
Formal statement
namespace NAGFlow.GradCorr

/-- Inequality (93) in the proof of Theorem 5.2 (Luo & Chen, arXiv:1909.03145v4, p. 22). Let
`f ∈ S¹_μ`, `x*` a global minimiser of `f`, and `(x, y, v)` a run of the corrected scheme (91) with
parameters `(α, γ)` from (73) (`γ₀ > 0`, any step sizes `α_k > 0`). With
`ℒ̂_k = f(y_k) − f(x*) + (γ_{k+1}/2)‖v_{k+1} − x*‖²` (84), for every `k`
`ℒ̂_k − ℒ_k ≤ −α_kℒ̂_k + (α_k²/(2γ_k))‖∇f(y_k)‖²`. -/
theorem eq_93 {V : Type*} [NormedAddCommGroup V] [InnerProductSpace ℝ V] [CompleteSpace V]
    (f : V → ℝ) (gradf : V → V) (μ L : ℝ) (hf : NAGFlow.PredCorr.IsS1 f gradf μ)
    (xstar : V) (hxstar : ∀ y, f xstar ≤ f y)
    (α γ : ℕ → ℝ) (hγ : NAGFlow.PredCorr.IsGammaRun μ α γ)
    (x y v : ℕ → V) (hrun : IsGCRun gradf μ L α γ x y v) (k : ℕ) :
    NAGFlow.PredCorr.lyapHat f xstar y v γ k - NAGFlow.PredCorr.lyap f xstar x v γ k ≤
      -α k * NAGFlow.PredCorr.lyapHat f xstar y v γ k + α k ^ 2 / (2 * γ k) * ‖gradf (y k)‖ ^ 2 := by sorry

end NAGFlow.GradCorr
Source
Luo & Chen, arXiv:1909.03145v4, proof of Theorem 5.2, Eq. (93), p. 22; (84) p. 20
Human review
  • Endorsed by Shuze Chen · Oct 10, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 10, 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