Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 3, (17), p. 419 — ‖∇f(x̄) − h(x)‖ ≤ (L/√n)‖x − 1x̄‖

Proved
StochGradTrack.Const.lemma_3

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

consensusdistributed-optimizationlipschitz-gradientp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let each ∇fi:Rp→Rp\nabla f_i:\mathbb R^p\to\mathbb R^p∇fi​:Rp→Rp be LLL-Lipschitz. For every stacked x∈Rn×p\mathbf x\in\mathbb R^{n\times p}x∈Rn×p with average xˉ\bar xxˉ, writing ∇f(xˉ)=1n∑i∇fi(xˉ)\nabla f(\bar x)=\frac1n\sum_i\nabla f_i(\bar x)∇f(xˉ)=n1​∑i​∇fi​(xˉ) and h(x)=1n∑i∇fi(xi)h(\mathbf x)=\frac1n\sum_i\nabla f_i(x_i)h(x)=n1​∑i​∇fi​(xi​),

∥∇f(xˉ)−h(x)∥≤Ln ∥x−1xˉ∥.\|\nabla f(\bar x)-h(\mathbf x)\|\le\frac{L}{\sqrt n}\,\|\mathbf x-\mathbf 1\bar x\| .∥∇f(xˉ)−h(x)∥≤n​L​∥x−1xˉ∥.

The page states this for the iterates xk\mathbf x_kxk​; it bounds how far the averaged local gradients are from the true gradient at the average, in terms of the consensus error.

Formalization Note. The page says "for all k≥0k\ge0k≥0" about xk\mathbf x_kxk​; the claim holds for every stacked x\mathbf xx and is stated so. Only the Lipschitz half of Assumption 2 is used. ∥x−1xˉ∥\|\mathbf x-\mathbf 1\bar x\|∥x−1xˉ∥ is the Frobenius norm.

Preamble
import Mathlib
import Definitions.Def_StochGradTrack_Const_Model
Formal statement
namespace StochGradTrack.Const

open MeasureTheory ProbabilityTheory Matrix

theorem lemma_3 {n p : ℕ} (gradf : Fin n → E p → E p) (L : ℝ)
    (hL : ∀ i (x x' : E p), ‖gradf i x - gradf i x'‖ ≤ L * ‖x - x'‖) (x : Stack n p) :
    ‖gradAvg gradf (avg x) - hAvg gradf x‖ ≤ L / Real.sqrt n * Real.sqrt (consErr x) := by sorry

end StochGradTrack.Const
Source
Pu & Nedić, Math. Program. 187 (2021), Lemma 3 with (17), p. 419
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