Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§3.3, proof of Theorem 3.8, pp. 272–273 — one step of Frank–Wolfe: δ_{s+1} ≤ (1 − γ_s)δ_s + (β/2)γ_s²R²

Proved
ConvexOptAlg.FrankWolfe.thm_3_8_step

by mikedeng1 · Oct 5, 2026 · Mathlib 0df444a (Lean v4.33.1)

convex-optimizationfrank-wolfep2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1

Let EEE be a finite-dimensional real normed space, X⊆E\mathcal X\subseteq EX⊆E nonempty, compact and convex, with diameter R=sup⁡x,y∈X∥x−y∥R=\sup_{x,y\in\mathcal X}\|x-y\|R=supx,y∈X​∥x−y∥, and let f:E→Rf:E\to\mathbb Rf:E→R be differentiable, convex on X\mathcal XX and β\betaβ-smooth with respect to ∥⋅∥\|\cdot\|∥⋅∥ on X\mathcal XX for some β≥0\beta\ge0β≥0. Let x∗∈Xx^*\in\mathcal Xx∗∈X minimize fff over X\mathcal XX. Let (xt,yt)t≥1(x_t,y_t)_{t\ge1}(xt​,yt​)t≥1​ be a run of conditional gradient descent on X\mathcal XX with step sizes γs∈[0,1]\gamma_s\in[0,1]γs​∈[0,1] for all s≥1s\ge1s≥1, and write δs=f(xs)−f(x∗)\delta_s=f(x_s)-f(x^*)δs​=f(xs​)−f(x∗). Then for every s≥1s\ge1s≥1,

δs+1≤(1−γs) δs+β2γs2R2.\delta_{s+1}\le(1-\gamma_s)\,\delta_s+\frac{\beta}{2}\gamma_s^2R^2 .δs+1​≤(1−γs​)δs​+2β​γs2​R2.

This one-step recursion is the whole content of the analysis of Theorem 3.8; the rate then follows from a scalar induction.

Formalization Note RRR is Metric.diam X, which is the supremum of ∥x−y∥\|x-y\|∥x−y∥ over x,y∈Xx,y\in\mathcal Xx,y∈X because X\mathcal XX is compact (hence bounded). The step sizes are required to lie in [0,1][0,1][0,1], which keeps every iterate in X\mathcal XX; the book applies the recursion only to γs=2/(s+1)\gamma_s=2/(s+1)γs​=2/(s+1), which satisfies this. β≥0\beta\ge0β≥0 is the usual reading of "β-smooth". The minimizer x∗x^*x∗ is the book's standing assumption (p. 242).

Preamble
import Mathlib
import Definitions.Def_ConvexOptAlg_FrankWolfe_Defs
Formal statement
namespace ConvexOptAlg.FrankWolfe

/-- Bubeck, arXiv:1405.4980v2, proof of Theorem 3.8, pp. 272–273 (the displayed chain and its
rewriting): for a run of conditional gradient descent with step sizes `γ_s ∈ [0, 1]` on a convex
`f`, β-smooth in an arbitrary norm, over a compact convex `X` with minimizer `x∗`, and
`R = sup_{x,y∈X} ‖x − y‖ = diam X`, the gaps `δ_s = f(x_s) − f(x∗)` satisfy, for every `s ≥ 1`,
`δ_{s+1} ≤ (1 − γ_s) δ_s + (β/2) γ_s² R²`. -/
theorem thm_3_8_step {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E] [FiniteDimensional ℝ E]
    (X : Set E) (hXc : IsCompact X) (hXconv : Convex ℝ X)
    (f : E → ℝ) (f' : E → E →L[ℝ] ℝ) (β : ℝ) (hβ : 0 ≤ β)
    (hf : ConvexOn ℝ X f) (hsmooth : IsBetaSmoothNormOn X f f' β)
    (xstar : E) (hxstar : xstar ∈ X) (hopt : ∀ z ∈ X, f xstar ≤ f z)
    (γ : ℕ → ℝ) (hγ : ∀ s : ℕ, 1 ≤ s → γ s ∈ Set.Icc (0 : ℝ) 1)
    (x y : ℕ → E) (hrun : IsFrankWolfeRun X f' γ x y)
    (s : ℕ) (hs : 1 ≤ s) :
    f (x (s + 1)) - f xstar ≤
      (1 - γ s) * (f (x s) - f xstar) + β / 2 * γ s ^ 2 * Metric.diam X ^ 2 := by sorry

end ConvexOptAlg.FrankWolfe
Source
Bubeck, arXiv:1405.4980v2, §3.3, proof of Theorem 3.8, pp. 272–273 (displayed chain and the δ_s recursion)
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