Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(35), p. 347 — (1 + μA_k)D_h(x, x^k) = D_{ψ_k}(x, x^k) ≤ ψ_k(x) − ψ*_k

Proved
RelSmoothFOM.DualAvg.eq_35

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

bregman-distancedual-averagingfirst-order-optimalityp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let QQQ be a convex subset of a finite-dimensional real inner-product space EEE, let f,hf, hf,h be convex on QQQ and differentiable at every point of QQQ, and let 0≤μ<L0 \le \mu < L0≤μ<L. Let (xk)(x^k)(xk) be a run of the dual averaging scheme (Algorithm 2) with models ψk\psi_kψk​ and ψk∗=ψk(xk)\psi^*_k = \psi_k(x^k)ψk∗​=ψk​(xk). Then for every k≥0k \ge 0k≥0 and every x∈Qx \in Qx∈Q,

(1+μAk) Dh(x,xk)=Dψk(x,xk)≤ψk(x)−ψk∗.(1 + \mu A_k)\, D_h(x, x^k) = D_{\psi_k}(x, x^k) \le \psi_k(x) - \psi^*_k .(1+μAk​)Dh​(x,xk)=Dψk​​(x,xk)≤ψk​(x)−ψk∗​.

The equality holds because ψk\psi_kψk​ is an affine function plus (1+μAk)h(1 + \mu A_k) h(1+μAk​)h, so the two have the same Bregman distance; the inequality is the first-order optimality condition of xkx^kxk for ψk\psi_kψk​ over QQQ. It is the step that turns the minimisation in Algorithm 2 into the growth estimate for ψk+1∗\psi^*_{k+1}ψk+1∗​.

Formalization Note DψkD_{\psi_k}Dψk​​ is the Bregman distance (7) of the function ψk\psi_kψk​, with its Fréchet derivative at xk∈Qx^k \in Qxk∈Q; ψk\psi_kψk​ is differentiable there because hhh is. No relative smoothness or relative strong convexity is assumed: neither is used.

Preamble
import Mathlib
import Definitions.Def_RelSmoothFOM_DualAvg_Setting
Formal statement
namespace RelSmoothFOM.DualAvg

/-- (35), proof of Theorem 3.2, p. 347: along a run of Algorithm 2, for every `k` and `u ∈ Q`,
`(1 + μA_k) D_h(u, x^k) = D_{ψ_k}(u, x^k) ≤ ψ_k(u) − ψ*_k`, where `ψ_k = daModel f h L μ x k`
and `ψ*_k = ψ_k(x^k)`. -/
theorem eq_35
    {E : Type*} [NormedAddCommGroup E] [InnerProductSpace ℝ E] [FiniteDimensional ℝ E]
    (Q : Set E) (hQ : Convex ℝ Q)
    (f h : E → ℝ) (hfd : ∀ x ∈ Q, DifferentiableAt ℝ f x) (hfc : ConvexOn ℝ Q f)
    (hhd : ∀ x ∈ Q, DifferentiableAt ℝ h x) (hhc : ConvexOn ℝ Q h)
    (L μ : ℝ) (hμ : 0 ≤ μ) (hμL : μ < L)
    (x : ℕ → E) (hrun : IsDualAveragingRun Q f h L μ x) :
    ∀ k : ℕ, ∀ u ∈ Q,
      (1 + μ * daSum L μ k) * bregman h u (x k) = bregman (daModel f h L μ x k) u (x k) ∧
      bregman (daModel f h L μ x k) u (x k) ≤
        daModel f h L μ x k u - daModel f h L μ x k (x k) := by sorry

end RelSmoothFOM.DualAvg
Source
Lu, Freund & Nesterov, Relatively smooth convex optimization by first-order methods, and applications, SIAM J. Optim. 28 (2018), p. 347, proof of Theorem 3.2, (35)
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