Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 1 — convergence or unboundedness of the Bregman proximal-point run

Proved
BregmanPPA.Convergence.theorem1

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

bregman-functionmonotone-operatorp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1proximal-point

Let TTT be maximal monotone on a finite-dimensional real inner-product space. Let hhh be a Bregman function with zone SSS, with dom⁡T⊆S‾\operatorname{dom}T\subseteq\overline SdomT⊆S. Let (ck)(c_k)(ck​) be positive and bounded below by a positive constant, and let (xk)(x^k)(xk) be an infinite Bregman proximal-point run. Assume either (C1) dom⁡T‾⊆S\overline{\operatorname{dom}T}\subseteq SdomT⊆S, or (C2) T=∂fT=\partial fT=∂f for a proper lower semicontinuous convex function fff. Then:

T−1(0)≠∅⟹xk→z for some z∈T−1(0),T−1(0)=∅ and (C1)⟹{xk:k≥0} is unbounded.\begin{aligned} T^{-1}(0)\ne\varnothing&\quad\Longrightarrow\quad x^k\to z\text{ for some }z\in T^{-1}(0),\\ T^{-1}(0)=\varnothing\ \text{and (C1)}&\quad\Longrightarrow\quad \{x^k:k\ge0\}\text{ is unbounded}. \end{aligned}T−1(0)=∅T−1(0)=∅ and (C1)​⟹xk→z for some z∈T−1(0),⟹{xk:k≥0} is unbounded.​

This is the paper's central convergence and divergence alternative for nonlinear proximal-point algorithms.

Formalization Note The space is a finite-dimensional real inner-product space, representing Rn\mathbb R^nRn. The run explicitly keeps every iterate in SSS and expresses (3) through the equivalent inclusion (4). The standing inclusion dom⁡T⊆S‾\operatorname{dom}T\subseteq\overline SdomT⊆S differs from (C1), dom⁡T‾⊆S\overline{\operatorname{dom}T}\subseteq SdomT⊆S. Unbounded means the range of the full sequence is not bounded.

Preamble
import Mathlib
import Definitions.Def_BregmanPPA_Convergence_Model

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

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

/-- Theorem 1: convergence to a zero, or unboundedness when there are no zeros under (C1). -/
theorem theorem1 (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)
    (hC : closure (dom T) ⊆ S ∨ ∃ f : H → EReal,
      IsProperFn f ∧ IsConvexFn f ∧ LowerSemicontinuous f ∧ T = subdiffOp f) :
    ((zer T).Nonempty → ∃ z : H, z ∈ zer T ∧ Tendsto x atTop (𝓝 z)) ∧
    (zer T = ∅ → closure (dom T) ⊆ S → ¬ 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), pp. 206–207, Theorem 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