Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 10, p. 22 — for f ∈ S_µ,L the speed restarted ODE satisfies f(Xˢʳ(t)) − f⋆ ≤ (c₁L‖x₀ − x⋆‖²/2) e^{−c₂t√L}

Proved
NesterovODE.Restart.theorem_10

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

linear-convergencenesterov-odep2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1speed-restart

There exist positive constants c1c_1c1​ and c2c_2c2​, depending only on the condition number L/μL/\muL/μ, with the following property. Let 0<μ≤L0<\mu\le L0<μ≤L, let f∈Sμ,Lf\in\mathcal S_{\mu,L}f∈Sμ,L​ on Rn\mathbb R^nRn with minimizer x⋆x^\starx⋆ and f⋆=f(x⋆)f^\star=f(x^\star)f⋆=f(x⋆), let x0∈Rnx_0\in\mathbb R^nx0​∈Rn, and let XsrX^{\mathrm{sr}}Xsr be the speed restarted trajectory from x0x_0x0​, the solution of (29). Then for every t≥0t\ge0t≥0,

f(Xsr(t))−f⋆≤c1L∥x0−x⋆∥22 e−c2tL.f(X^{\mathrm{sr}}(t))-f^\star\le\frac{c_1L\|x_0-x^\star\|^2}2\,e^{-c_2t\sqrt L}.f(Xsr(t))−f⋆≤2c1​L∥x0​−x⋆∥2​e−c2​tL​.

Resetting the friction of the Nesterov ODE whenever the speed stops increasing yields linear convergence for strongly convex objectives without knowledge of μ\muμ, in contrast with the polynomial rates of the unrestarted ODE.

Formalization Note c1c_1c1​ and c2c_2c2​ are functions of the condition number, ci=ci(L/μ)c_i=c_i(L/\mu)ci​=ci​(L/μ), chosen before the dimension, fff, μ\muμ, LLL, x0x_0x0​ and the trajectory; this is "only depend on the condition number L/μL/\muL/μ". The statement covers every curve satisfying the speed-restart predicate of the Setting definition; in particular it covers x0=x⋆x_0=x^\starx0​=x⋆, where the trajectory stays at x⋆x^\starx⋆. The predicate does not assume that the restart times tend to infinity: that is a consequence of Lemma 25.

Preamble
import Mathlib
import Definitions.Def_NesterovODE_Restart_Setting
Formal statement
namespace NesterovODE.Restart

open scoped RealInnerProductSpace

/-- Theorem 10 (p. 22): there are positive constants `c₁, c₂` depending only on the condition
number `L/μ` (functions of `L/μ`, chosen before the dimension, `f`, `μ`, `L`, `x₀`) such that
every speed restarted trajectory satisfies
`f(Xˢʳ(t)) − f⋆ ≤ (c₁L‖x₀ − x⋆‖²/2) e^{−c₂ t √L}` for all `t ≥ 0`. -/
theorem theorem_10 :
    ∃ c₁ c₂ : ℝ → ℝ, (∀ κ : ℝ, 0 < c₁ κ ∧ 0 < c₂ κ) ∧
      ∀ (n : ℕ) (f : NesterovODE.WellPosed.E n → ℝ) (μ : ℝ) (L : NNReal),
        0 < μ → μ ≤ L → NesterovODE.StrongCvx.InSMuL μ L f →
        ∀ (x₀ xstar : NesterovODE.WellPosed.E n), (∀ y, f xstar ≤ f y) →
        ∀ Xsr : ℝ → NesterovODE.WellPosed.E n, IsSpeedRestarted f x₀ Xsr →
        ∀ t : ℝ, 0 ≤ t →
          f (Xsr t) - f xstar ≤
            c₁ (L / μ) * L * ‖x₀ - xstar‖ ^ 2 / 2 *
              Real.exp (-(c₂ (L / μ)) * t * Real.sqrt L) := by sorry

end NesterovODE.Restart
Source
Su, Boyd, Candès, A Differential Equation for Modeling Nesterov's Accelerated Gradient Method, arXiv:1503.01243v2, p. 22, Theorem 10 (proof pp. 24–25)
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