Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§6, display after (6.5) — 1k+1δ~k(D)≥1k+1∑i[f(x~i,ξ~i)−f(x∗,ξ~i)]\frac{1}{k+1}\tilde\delta_k(D) \ge \frac{1}{k+1}\sum_i[f(\tilde x_i,\tilde\xi_i) - f(x^*,\tilde\xi_i)]k+11​δ~k​(D)≥k+11​∑i​[f(x~i​,ξ~​i​)−f(x∗,ξ~​i​)] for D≥d(x∗)D \ge d(x^*)D≥d(x∗)

Proved
PrimalDualSubgrad.Stoch.gap_lower_bound

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

convex-optimizationdual-averagingp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1stochastic-optimization

Under the standing assumptions of §6, let x∗∈Qx^* \in Qx∗∈Q be a minimizer of φ(x)=Eξf(x,ξ)\varphi(x) = \mathbb E_\xi f(x,\xi)φ(x)=Eξ​f(x,ξ) over QQQ. Fix γ>0\gamma > 0γ>0 and a realization ξ~0,ξ~1,…\tilde\xi_0, \tilde\xi_1, \dotsξ~​0​,ξ~​1​,… of the samples, let x~i\tilde x_ix~i​ be the points of the method of stochastic simple averages (6.3) on it and δ~k(D)\tilde\delta_k(D)δ~k​(D) the gap (6.4). If D≥d(x∗)D \ge d(x^*)D≥d(x∗), then for every k≥0k \ge 0k≥0

1k+1δ~k(D) ≥ 1k+1∑i=0k⟨f′(x~i,ξ~i),x~i−x∗⟩ ≥ 1k+1∑i=0k[f(x~i,ξ~i)−f(x∗,ξ~i)].\frac{1}{k+1}\tilde\delta_k(D) \ \ge\ \frac{1}{k+1}\sum_{i=0}^k \langle f'(\tilde x_i, \tilde\xi_i), \tilde x_i - x^*\rangle \ \ge\ \frac{1}{k+1}\sum_{i=0}^k \big[f(\tilde x_i, \tilde\xi_i) - f(x^*, \tilde\xi_i)\big].k+11​δ~k​(D) ≥ k+11​i=0∑k​⟨f′(x~i​,ξ~​i​),x~i​−x∗⟩ ≥ k+11​i=0∑k​[f(x~i​,ξ~​i​)−f(x∗,ξ~​i​)].

The gap of a run therefore dominates the average excess cost of the visited points against the optimum on the same samples; this is the second step of the proof of Theorem 7.

Formalization Note Sk=k+1S_k = k+1Sk​=k+1. The two inequalities are stated as a conjunction, each written with ≤\le≤.

Preamble
import Mathlib
import Definitions.Def_PrimalDualSubgrad_Stoch_ProxSetting
import Definitions.Def_PrimalDualSubgrad_Stoch_SSA
Formal statement
namespace PrimalDualSubgrad.Stoch

open Finset MeasureTheory

variable {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E] [FiniteDimensional ℝ E]
  [MeasurableSpace E] [BorelSpace E]
variable {Ξ : Type*} [MeasurableSpace Ξ]

/-- Nesterov 2009, §6, display after (6.5), p. 26: for `D ≥ d(x*)` and every sample path,
`(1/S_k) δ̃_k(D) ≥ (1/(k+1)) Σ ⟨f'(x̃_i, ξ̃_i), x̃_i − x*⟩ ≥ (1/(k+1)) Σ [f(x̃_i, ξ̃_i) − f(x*, ξ̃_i)]`
(the two inequalities as a conjunction, the first written right-to-left). -/
theorem gap_lower_bound (Q : Set E) (d : E → ℝ) (σ : ℝ) (x0 : E) (hd : ProxFunction Q d σ x0)
    (π : ℝ → StrongDual ℝ E → E) (hπ : IsArgminMap Q d π)
    (μ : Measure Ξ) [IsProbabilityMeasure μ] (f : E → Ξ → ℝ) (f' : E → Ξ → StrongDual ℝ E)
    (L : ℝ) (hf : StochOracle Q μ f f' L)
    (xstar : E) (hxstar : xstar ∈ Q)
    (hmin : ∀ x ∈ Q, expectedCost μ f xstar ≤ expectedCost μ f x)
    (γ : ℝ) (hγ : 0 < γ) (ω : ℕ → Ξ) (k : ℕ) (D : ℝ) (hD : d xstar ≤ D) :
    1 / ((k : ℝ) + 1) * ∑ i ∈ range (k + 1), f' (ssaRun π γ x0 f' ω i) (ω i) (ssaRun π γ x0 f' ω i - xstar)
        ≤ 1 / ((k : ℝ) + 1) * gap Q d (fun i => f' (ssaRun π γ x0 f' ω i) (ω i)) (ssaRun π γ x0 f' ω) k D ∧
      1 / ((k : ℝ) + 1) * ∑ i ∈ range (k + 1), (f (ssaRun π γ x0 f' ω i) (ω i) - f xstar (ω i))
        ≤ 1 / ((k : ℝ) + 1) * ∑ i ∈ range (k + 1), f' (ssaRun π γ x0 f' ω i) (ω i) (ssaRun π γ x0 f' ω i - xstar) := by sorry

end PrimalDualSubgrad.Stoch
Source
Nesterov, Primal-dual subgradient methods for convex problems, Math. Program. 120 (2009), §6, display after (6.5), p. 26
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