Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 3.2, pp. 540–541 — one-step Bregman descent inequality (13)

Proved
ChenTeboullePMD.Rate.lemma_3_2

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

bregman-functionconvex-optimizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1proximal-point

Let fff be a proper lower semicontinuous convex extended-valued objective with effective domain CCC, let ψ\psiψ be a Bregman function with zone SSS containing the relative interior of CCC, and let (xk)(x^k)(xk) be a PMD run with positive steps λk\lambda_kλk​. For every k≥1k\ge1k≥1 and u∈C∩Sˉu\in C\cap\bar Su∈C∩Sˉ,

λk(f(xk)−f(u))≤Dψ(u,xk−1)−Dψ(u,xk)−Dψ(xk,xk−1).\lambda_k\bigl(f(x^k)-f(u)\bigr) \le D_\psi(u,x^{k-1})-D_\psi(u,x^k)-D_\psi(x^k,x^{k-1}).λk​(f(xk)−f(u))≤Dψ​(u,xk−1)−Dψ​(u,xk)−Dψ​(xk,xk−1).

This is the one-step estimate from which the weighted telescoping bound follows.

Formalization Note The ambient space is any finite-dimensional real normed space, with gradients represented by covectors. The extended objective is encoded by CCC and real fff on CCC. The page's u∈Sˉu\in\bar Su∈Sˉ outside CCC has f(u)=+∞f(u)=+\inftyf(u)=+∞ and yields a trivial extended-valued comparison; the displayed real inequality covers its nontrivial domain. The PMD run predicate replaces the assumption that ∇ψ\nabla\psi∇ψ is onto, which the page uses to ensure the iterates exist.

Preamble
import Mathlib
import Definitions.Def_BeckTeboulleMD_EMDA_Setting
import Definitions.Def_ChenTeboullePMD_Rate_Setting
Formal statement
namespace ChenTeboullePMD.Rate

open BeckTeboulleMD.EMDA

/-- Lemma 3.2, display (13), pp. 540–541. -/
theorem lemma_3_2 {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E]
    [FiniteDimensional ℝ E]
    (S : Set E) (ψ : E → ℝ) (hψ : IsBregmanFunction S ψ)
    (C : Set E) (hCne : C.Nonempty) (hCconv : Convex ℝ C)
    (f : E → ℝ) (hf : ConvexOn ℝ C f)
    (hlsc : LowerSemicontinuous (extendTop C f))
    (hri : intrinsicInterior ℝ C ⊆ S)
    (lam : ℕ → ℝ) (hlam : ∀ k, 1 ≤ k → 0 < lam k)
    (x : ℕ → E) (hrun : IsPMDRun S C ψ f lam x) :
    ∀ k : ℕ, ∀ u ∈ C, u ∈ closure S →
      lam (k + 1) * (f (x (k + 1)) - f u) ≤
        bregman ψ u (x k) - bregman ψ u (x (k + 1)) -
          bregman ψ (x (k + 1)) (x k) := by sorry

end ChenTeboullePMD.Rate
Source
Chen & Teboulle, Convergence analysis of a proximal-like minimization algorithm using Bregman functions, SIAM J. Optim. 3 (1993), pp. 540–541, Lemma 3.2, (13)
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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