Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§2, (2), p. 2 — an LLL-Lipschitz gradient gives f(y)≤f(x)+⟨∇f(x),y−x⟩+L2∥y−x∥2f(y) \le f(x) + \langle \nabla f(x), y - x\rangle + \frac L2\|y - x\|^2f(y)≤f(x)+⟨∇f(x),y−x⟩+2L​∥y−x∥2

Proved
KarimiPL.Prox.quadUpper_of_lipschitz

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

descent-lemmap2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1smoothness

Let f:Rd→Rf : \mathbb R^d \to \mathbb Rf:Rd→R be differentiable with an LLL-Lipschitz continuous gradient,

∥∇f(x)−∇f(y)∥≤L ∥x−y∥for all x,y∈Rd.\|\nabla f(x) - \nabla f(y)\| \le L\,\|x - y\| \qquad \text{for all } x, y \in \mathbb R^d.∥∇f(x)−∇f(y)∥≤L∥x−y∥for all x,y∈Rd.

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

This is the quadratic upper bound (2) that the paper derives from its standing assumption of an LLL-Lipschitz gradient, and the only place the Lipschitz assumption enters the proof of Theorem 5.

Formalization Note The conclusion is the published predicate ShiOptRates.QuadUpper f (gradient f) L. The same statement is a milestone of mission I of this series; drafts cannot import drafts, so it is restated here.

Preamble
import Mathlib
import Definitions.Def_ShiOptrates_FunctionClass
import Definitions.Def_KarimiPL_Prox_Setting

open InnerProductSpace
Formal statement
namespace KarimiPL.Prox

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.Prox
Source
Karimi, Nutini, Schmidt, arXiv:1608.04636v4, §2, (2), 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