Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 3.1, p. 345 — three-point property: φ(x) + D_h(x,z) ≥ φ(z⁺) + D_h(z⁺,z) + D_h(x,z⁺)

Proved
RelSmoothFOM.PrimalGrad.lemma_3_1

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

bregman-distancefirst-order-methodsp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1three-point-property

This is the three-point property of Tseng.

Let QQQ be a convex subset of a finite-dimensional real inner-product space EEE, let h:E→Rh:E\to\mathbb Rh:E→R be differentiable at every point of QQQ and convex on QQQ, and let Dh(y,x)=h(y)−h(x)−⟨∇h(x),y−x⟩D_h(y,x)=h(y)-h(x)-\langle\nabla h(x),y-x\rangleDh​(y,x)=h(y)−h(x)−⟨∇h(x),y−x⟩ be its Bregman distance. Let φ\varphiφ be convex on QQQ, let z∈Qz\in Qz∈Q, and let z+∈Qz^+\in Qz+∈Q be a minimiser over QQQ of x↦φ(x)+Dh(x,z)x\mapsto\varphi(x)+D_h(x,z)x↦φ(x)+Dh​(x,z). Then

φ(x)+Dh(x,z)  ≥  φ(z+)+Dh(z+,z)+Dh(x,z+)for all x∈Q.\varphi(x)+D_h(x,z)\;\ge\;\varphi(z^+)+D_h(z^+,z)+D_h(x,z^+)\qquad\text{for all }x\in Q.φ(x)+Dh​(x,z)≥φ(z+)+Dh​(z+,z)+Dh​(x,z+)for all x∈Q.

The lemma quantifies how much the proximal objective grows when one moves from the minimiser z+z^+z+ to any other feasible point, in terms of the Bregman distance from z+z^+z+. It is the step that turns one iteration of a Bregman proximal method into a telescoping inequality.

Formalization Note The minimiser z+z^+z+ is a hypothesis on a given point (it minimises over QQQ), not a value of an argmin operator, so no existence or uniqueness of minimisers is assumed or claimed. The function φ\varphiφ need not be differentiable. z∈Qz\in Qz∈Q is assumed because the paper's Bregman distance (7) is defined on Q×QQ\times QQ×Q.

Preamble
import Mathlib
import Definitions.Def_RelSmoothFOM_PrimalGrad_Setting
Formal statement
namespace RelSmoothFOM.PrimalGrad

theorem lemma_3_1 {E : Type*} [NormedAddCommGroup E] [InnerProductSpace ℝ E]
    [FiniteDimensional ℝ E]
    (Q : Set E) (hQ : Convex ℝ Q) (φ : E → ℝ) (hφ : ConvexOn ℝ Q φ) (h : E → ℝ)
    (hhd : ∀ x ∈ Q, DifferentiableAt ℝ h x) (hhc : ConvexOn ℝ Q h)
    (z zp : E) (hz : z ∈ Q) (hzp : zp ∈ Q)
    (hmin : ∀ u ∈ Q, φ zp + bregman h zp z ≤ φ u + bregman h u z) :
    ∀ u ∈ Q, φ u + bregman h u z ≥ φ zp + bregman h zp z + bregman h u zp := by sorry

end RelSmoothFOM.PrimalGrad
Source
Lu, Freund & Nesterov, Relatively smooth convex optimization by first-order methods, and applications, SIAM J. Optim. 28 (2018), p. 345, Lemma 3.1
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