Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§3.2, proof of Theorem 3.3, p. 268 — the gaps δ_s satisfy δ_{s+1} ≤ δ_s − δ_s²/(2β‖x₁ − x*‖²)

Proved
ConvexOptAlg.SmoothGD.thm_3_3_recursion

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

convex-optimizationgradient-descentp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1

Let f:Rn→Rf:\mathbb R^n\to\mathbb Rf:Rn→R be convex and β\betaβ-smooth with β>0\beta>0β>0, let x∗x^*x∗ be a minimizer of fff, and let (xs)s≥1(x_s)_{s\ge1}(xs​)s≥1​ be gradient descent with η=1/β\eta=1/\betaη=1/β. 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,

δs2≤2β∥x1−x∗∥2 (δs−δs+1),\delta_s^2\le 2\beta\|x_1-x^*\|^2\,(\delta_s-\delta_{s+1}),δs2​≤2β∥x1​−x∗∥2(δs​−δs+1​),

that is, when x1≠x∗x_1\ne x^*x1​=x∗,

δs+1≤δs−12β∥x1−x∗∥2 δs2.\delta_{s+1}\le\delta_s-\frac{1}{2\beta\|x_1-x^*\|^2}\,\delta_s^2.δs+1​≤δs​−2β∥x1​−x∗∥21​δs2​.

This one-step recursion on the optimality gaps is what the proof of Theorem 3.3 turns into the 1/(t−1)1/(t-1)1/(t−1) rate.

Formalization Note The page writes the recursion with ∥x1−x∗∥2\|x_1-x^*\|^2∥x1​−x∗∥2 in a denominator; the Lean statement is multiplied through by 2β∥x1−x∗∥22\beta\|x_1-x^*\|^22β∥x1​−x∗∥2, which is equivalent when x1≠x∗x_1\ne x^*x1​=x∗ and remains true (with both sides 000) when x1=x∗x_1=x^*x1​=x∗. The minimizer's existence is the book's standing assumption; β>0\beta>0β>0 is implicit (η=1/β\eta=1/\betaη=1/β).

Preamble
import Mathlib
import Definitions.Def_ConvexOptAlg_SmoothGD_Defs
open scoped InnerProductSpace
Formal statement
namespace ConvexOptAlg.SmoothGD

/-- Proof of Theorem 3.3, last display on p. 268 (Bubeck, arXiv:1405.4980v2), multiplied out: for
gradient descent with `η = 1/β` on a convex β-smooth `f` (β > 0) with a minimizer `x*`, writing
`δ_s = f(x_s) − f(x*)`, for every `s ≥ 1`,
`δ_s² ≤ 2β‖x₁ − x*‖² (δ_s − δ_{s+1})`, i.e. `δ_{s+1} ≤ δ_s − δ_s²/(2β‖x₁ − x*‖²)` when `x₁ ≠ x*`;
the multiplied form also covers `x₁ = x*`. -/
theorem thm_3_3_recursion {n : ℕ} (f : EuclideanSpace ℝ (Fin n) → ℝ)
    (g : EuclideanSpace ℝ (Fin n) → EuclideanSpace ℝ (Fin n)) (β : ℝ) (hβ : 0 < β)
    (hconv : ConvexOn ℝ Set.univ f) (hf : IsBetaSmooth f g β)
    (xstar : EuclideanSpace ℝ (Fin n)) (hmin : ∀ y, f xstar ≤ f y)
    (x : ℕ → EuclideanSpace ℝ (Fin n)) (hrun : IsGDRun g (1 / β) x) (s : ℕ) (hs : 1 ≤ s) :
    (f (x s) - f xstar) ^ 2 ≤
      2 * β * ‖x 1 - xstar‖ ^ 2 * ((f (x s) - f xstar) - (f (x (s + 1)) - f xstar)) := by sorry

end ConvexOptAlg.SmoothGD
Source
Bubeck, arXiv:1405.4980v2, §3.2, proof of Theorem 3.3, last display on p. 268
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