Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§2, equation (2) — an L-Lipschitz gradient gives the quadratic upper bound

Proved
KarimiPL.GD.quadUpper_of_lipschitz

by mikedeng1 · Oct 8, 2026 · Mathlib 0df444a (Lean v4.33.1)

gradient-descentlinear-convergencep2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1polyak-lojasiewicz

Let f:Rd→Rf:\mathbb R^d\to\mathbb Rf:Rd→R be differentiable and let its gradient be LLL-Lipschitz: ∥∇f(x)−∇f(y)∥≤L∥x−y∥\|\nabla f(x)-\nabla f(y)\|\le L\|x-y\|∥∇f(x)−∇f(y)∥≤L∥x−y∥ for all x,yx,yx,y. Then, for all x,y∈Rdx,y\in\mathbb R^dx,y∈Rd,

f(y)≤f(x)+⟨∇f(x),y−x⟩+L2∥y−x∥2.f(y)\le f(x)+\langle\nabla f(x),y-x\rangle+\frac L2\|y-x\|^2.f(y)≤f(x)+⟨∇f(x),y−x⟩+2L​∥y−x∥2.

This is the smoothness inequality (2) used in the rate proof. It relates the paper's Lipschitz-gradient assumption to the quadratic upper-bound predicate reused by the one-step results.

Formalization Note The statement does not require L>0L>0L>0: the implication from a Lipschitz bound to the displayed inequality also covers the degenerate point space d=0d=0d=0. The main theorem assumes L>0L>0L>0 because its step size divides by LLL.

Preamble
import Mathlib
import Definitions.Def_ShiOptrates_FunctionClass
open scoped InnerProductSpace
Formal statement
namespace KarimiPL.GD

theorem quadUpper_of_lipschitz {d : ℕ}
    (f : EuclideanSpace ℝ (Fin d) → ℝ)
    (hdiff : Differentiable ℝ f)
    (L : ℝ) (hLip : ∀ x y, ‖gradient f x - gradient f y‖ ≤ L * ‖x - y‖) :
    ShiOptRates.QuadUpper f (gradient f) L := by sorry

end KarimiPL.GD
Source
Karimi, Nutini, Schmidt, arXiv:1608.04636v4, §2, equation (2) and preceding sentence, p. 2
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