Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 1, Step 1 — decreasing Bregman distances and bounded iterates

Proved
BregmanPPA.Convergence.step1

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

bregman-functionp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1proximal-point

Consider a Bregman proximal-point run (xk)(x^k)(xk) for a maximal monotone operator TTT with dom⁡T⊆S‾\operatorname{dom}T\subseteq\overline SdomT⊆S, positive step sizes bounded below by a positive constant, and a Bregman function hhh with zone SSS. For every zero zzz of TTT and every k≥0k\ge0k≥0,

Dh(z,xk+1)≤Dh(z,xk)−Dh(xk+1,xk).D_h(z,x^{k+1})\le D_h(z,x^k)-D_h(x^{k+1},x^k).Dh​(z,xk+1)≤Dh​(z,xk)−Dh​(xk+1,xk).

Moreover, Dh(z,xk)D_h(z,x^k)Dh​(z,xk) tends to a nonnegative real limit and the sequence (xk)(x^k)(xk) is bounded.

This gives the distance and compactness estimates used in the convergence argument.

Formalization Note The paper's Step 1 writes T−1(0)⊆ST^{-1}(0)\subseteq ST−1(0)⊆S; under (C2), the stated standing assumption yields only T−1(0)⊆S‾T^{-1}(0)\subseteq\overline ST−1(0)⊆S. The inequality and boundedness use this latter inclusion, since Definition 1 defines DhD_hDh​ on S‾×S\overline S\times SS×S.

Preamble
import Mathlib
import Definitions.Def_BregmanPPA_Convergence_Model

open ThreeOpSplitting.Convergence Filter Topology
Formal statement
namespace BregmanPPA.Convergence

variable {H : Type*} [NormedAddCommGroup H] [InnerProductSpace ℝ H] [FiniteDimensional ℝ H]

/-- Theorem 1, proof, Step 1: decreasing Bregman distance and bounded iterates. -/
theorem step1 (T : H → Set H) (S : Set H) (h : H → ℝ) (c : ℕ → ℝ) (x : ℕ → H)
    (hT : IsMaximalMonotone T) (hh : IsBregmanFunction S h)
    (hdom : dom T ⊆ closure S) (hc : ∀ k, 0 < c k)
    (hcinf : ∃ ε : ℝ, 0 < ε ∧ ∀ k, ε ≤ c k)
    (hx : IsBregmanPPARun S h T c x) (z : H) (hz : z ∈ zer T) :
    (∀ k, bregmanD h z (x (k + 1)) ≤
      bregmanD h z (x k) - bregmanD h (x (k + 1)) (x k)) ∧
    (∃ δ : ℝ, 0 ≤ δ ∧ Tendsto (fun k => bregmanD h z (x k)) atTop (𝓝 δ)) ∧
    Bornology.IsBounded (Set.range x) := by sorry

end BregmanPPA.Convergence
Source
Eckstein, Nonlinear proximal point algorithms using Bregman functions, with applications to convex programming, Math. Oper. Res. 18(1) (1993), p. 207, Theorem 1 proof, Step 1, https://doi.org/10.1287/moor.18.1.202
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