Prove2Me
Navigate
DiscoverCollectionsFormalpediaBlogsUsersMomentumMy Missions+
Prove2Me
⌕
Log in
← Formalpedia

Theorem 2, p. 14 — for f ∈ S²_{μ,L} and 0 < s ≤ 1/L, the high-resolution heavy-ball ODE satisfies f(X(t)) − f(x⋆) ≤ 7‖x₀ − x⋆‖² e^{−√μ t/4}/(2s)

Proved
HighResODE.HeavyBallODE.theorem_2

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

heavy-ballhigh-resolution-odelinear-convergencep2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1strongly-convex

Theorem 2 (Convergence of the heavy-ball ODE). Let f∈Sμ,L2(Rn)f\in\mathcal S^2_{\mu,L}(\mathbb R^n)f∈Sμ,L2​(Rn), that is, fff is twice continuously differentiable with Lipschitz-continuous Hessian, LLL-smooth, and μ\muμ-strongly convex with 0<μ≤L0<\mu\le L0<μ≤L, and let x⋆x^\starx⋆ be its minimizer. Fix a step size 0<s≤1/L0<s\le 1/L0<s≤1/L and an initial point x0∈Rnx_0\in\mathbb R^nx0​∈Rn, and let X=X(t)X=X(t)X=X(t) be the solution of the high-resolution ODE of the heavy-ball method,

X¨(t)+2μ X˙(t)+(1+μs)∇f(X(t))=0,X(0)=x0,X˙(0)=−2s ∇f(x0)1+μs.\ddot X(t)+2\sqrt\mu\,\dot X(t)+\bigl(1+\sqrt{\mu s}\bigr)\nabla f(X(t))=0,\qquad X(0)=x_0,\quad\dot X(0)=-\frac{2\sqrt s\,\nabla f(x_0)}{1+\sqrt{\mu s}} .X¨(t)+2μ​X˙(t)+(1+μs​)∇f(X(t))=0,X(0)=x0​,X˙(0)=−1+μs​2s​∇f(x0​)​.

Then for every t≥0t\ge0t≥0,

f(X(t))−f(x⋆)≤7 ∥x0−x⋆∥22s e−μ t/4.f(X(t))-f(x^\star)\le\frac{7\,\|x_0-x^\star\|^2}{2s}\,e^{-\sqrt\mu\,t/4}.f(X(t))−f(x⋆)≤2s7∥x0​−x⋆∥2​e−μ​t/4.

The high-resolution ODE keeps the O(s)O(\sqrt s)O(s​) terms that the classical low-resolution limit discards. The theorem shows that this continuous-time model of Polyak's heavy-ball method converges linearly at the accelerated rate e−μt/4e^{-\sqrt\mu t/4}e−μ​t/4; in the paper it is contrasted with the high-resolution ODE of NAG-SC (Theorem 1), which carries an additional gradient-correction term.

Formalization Note. Rn\mathbb R^nRn is EuclideanSpace ℝ (Fin n). The solution is any pair (X,V)(X,V)(X,V) of curves with VVV the derivative of XXX and −2μV−(1+μs)∇f(X)-2\sqrt\mu V-(1+\sqrt{\mu s})\nabla f(X)−2μ​V−(1+μs​)∇f(X) the derivative of VVV on [0,∞)[0,\infty)[0,∞) (one-sided at 000), satisfying the two initial conditions; since the solution is unique (Proposition 2.1 of the paper), quantifying over all solutions is the paper's statement. The minimizer is a point x⋆x^\starx⋆ with f(x⋆)≤f(z)f(x^\star)\le f(z)f(x⋆)≤f(z) for all zzz, which exists for strongly convex fff.

Preamble
import Mathlib
import Definitions.Def_HighResODE_HeavyBallODE_Setting
Formal statement
namespace HighResODE.HeavyBallODE

theorem theorem_2 {n : ℕ} (f : HighResODE.NAGSC.E n → ℝ) (μ L s : ℝ) (hf : IsS2 f μ L) (xs : HighResODE.NAGSC.E n)
    (hmin : ∀ z : HighResODE.NAGSC.E n, f xs ≤ f z) (hs : 0 < s) (hsL : s ≤ 1 / L) (x0 : HighResODE.NAGSC.E n) (X V : ℝ → HighResODE.NAGSC.E n)
    (hsol : IsHeavyBallODE f μ s x0 X V) :
    ∀ t : ℝ, 0 ≤ t →
      f (X t) - f xs ≤ 7 * ‖x0 - xs‖ ^ 2 / (2 * s) * Real.exp (-(Real.sqrt μ * t / 4)) := by sorry

end HighResODE.HeavyBallODE
Source
Shi, Du, Jordan & Su, Understanding the Acceleration Phenomenon via High-Resolution Differential Equations, arXiv:1810.08907v3, p. 14, Theorem 2
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 paper
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me