Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(8), p. 10, and (IPAHD), p. 11 — every run of (IPAHD) satisfies the implicit discretization (8)

Proved
HessianDamping.IPAHD.run_satisfies_eq8

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

hessian-dampinginertial-algorithmp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1proximal-algorithm

Let H\mathcal HH be a real Hilbert space and f:H→Rf:\mathcal H\to\mathbb Rf:H→R a convex function of class C1\mathcal C^1C1. Let α≥1\alpha\ge1α≥1, h>0h>0h>0, s=h2s=h^2s=h2, and let (βk)(\beta_k)(βk​), (bk)(b_k)(bk​) be non-negative sequences. If (xk)k∈N(x_k)_{k\in\mathbb N}(xk​)k∈N​ is generated by (IPAHD), i.e. xk+1=proxμkf(yk)x_{k+1}=\mathrm{prox}_{\mu_kf}(y_k)xk+1​=proxμk​f​(yk​) for every k≥1k\ge1k≥1 with μk=kk+α(βks+sbk)\mu_k=\frac{k}{k+\alpha}(\beta_k\sqrt s+sb_k)μk​=k+αk​(βk​s​+sbk​) and yk=xk+(1−αk+α)(xk−xk−1)+βks(1−αk+α)∇f(xk)y_k=x_k+(1-\frac{\alpha}{k+\alpha})(x_k-x_{k-1})+\beta_k\sqrt s(1-\frac{\alpha}{k+\alpha})\nabla f(x_k)yk​=xk​+(1−k+αα​)(xk​−xk−1​)+βk​s​(1−k+αα​)∇f(xk​), then for every k≥1k\ge1k≥1

k(xk+1−2xk+xk−1)+α(xk+1−xk)+βkhk(∇f(xk+1)−∇f(xk))+bkh2k ∇f(xk+1)=0.(8)k(x_{k+1}-2x_k+x_{k-1})+\alpha(x_{k+1}-x_k)+\beta_khk\big(\nabla f(x_{k+1})-\nabla f(x_k)\big)+b_kh^2k\,\nabla f(x_{k+1})=0. \tag{8}k(xk+1​−2xk​+xk−1​)+α(xk+1​−xk​)+βk​hk(∇f(xk+1​)−∇f(xk​))+bk​h2k∇f(xk+1​)=0.(8)

The paper obtains (IPAHD) from the implicit discretization (8) of the continuous dynamic; this statement is the converse direction, the one the proof of Theorem 4 uses.

Formalization Note. The hypotheses h>0h>0h>0 and βk,bk≥0\beta_k,b_k\ge0βk​,bk​≥0 are implicit on the page (the step size is positive, μk≥0\mu_k\ge0μk​≥0 for the proximal step); see the Setting definition for the encoding of the proximal step.

Preamble
import Mathlib
import Definitions.Def_GoldenRatioVI_Shared_IsProxPoint
import Definitions.Def_HessianDamping_IPAHD_Setting
Formal statement
namespace HessianDamping.IPAHD

/-- (8), p. 10, and (IPAHD), p. 11: every run of (IPAHD) satisfies the implicit discretization (8). -/
theorem run_satisfies_eq8
    {H : Type*} [NormedAddCommGroup H] [InnerProductSpace ℝ H] [CompleteSpace H]
    (f : H → ℝ) (hfconv : ConvexOn ℝ Set.univ f) (hfC1 : ContDiff ℝ 1 f)
    (α : ℝ) (hα : 1 ≤ α)
    (h s : ℝ) (hh : 0 < h) (hs : s = h ^ 2)
    (β b : ℕ → ℝ) (hβ : ∀ k, 0 ≤ β k) (hb : ∀ k, 0 ≤ b k)
    (x : ℕ → H) (hx : IsIPAHDRun f α s β b x)
    (k : ℕ) (hk : 1 ≤ k) :
    (k : ℝ) • (x (k + 1) - (2 : ℝ) • x k + x (k - 1)) + α • (x (k + 1) - x k)
      + (β k * h * k) • (gradient f (x (k + 1)) - gradient f (x k))
      + (b k * h ^ 2 * k) • gradient f (x (k + 1)) = 0 := by sorry

end HessianDamping.IPAHD
Source
Attouch, Chbani, Fadili, Riahi, First-order optimization algorithms via inertial systems with Hessian driven damping, arXiv:1907.10536v2, §3.1.1, (8), p. 10, and (IPAHD), p. 11
Human review
  • Endorsed by Shuze Chen · Oct 8, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 8, 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