Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§3.2, proof of Theorem 3.3, p. 269 — gradient descent with η = 1/β does not increase ‖x_s − x*‖

Proved
ConvexOptAlg.SmoothGD.thm_3_3_dist_decrease

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, and let x∗x^*x∗ be a minimizer of fff on Rn\mathbb R^nRn. Let (xs)s≥1(x_s)_{s\ge1}(xs​)s≥1​ be gradient descent with step size η=1/β\eta=1/\betaη=1/β, xs+1=xs−1β∇f(xs)x_{s+1}=x_s-\frac1\beta\nabla f(x_s)xs+1​=xs​−β1​∇f(xs​). Then for every s≥1s\ge1s≥1,

∥xs+1−x∗∥2≤∥xs−x∗∥2−1β2∥∇f(xs)∥2,hence∥xs+1−x∗∥≤∥xs−x∗∥.\|x_{s+1}-x^*\|^2\le\|x_s-x^*\|^2-\frac1{\beta^2}\|\nabla f(x_s)\|^2,\qquad\text{hence}\qquad \|x_{s+1}-x^*\|\le\|x_s-x^*\|.∥xs+1​−x∗∥2≤∥xs​−x∗∥2−β21​∥∇f(xs​)∥2,hence∥xs+1​−x∗∥≤∥xs​−x∗∥.

This is the last step of the proof of Theorem 3.3: the distance to the minimizer is non-increasing along the iterates.

Formalization Note The existence of the minimizer x∗x^*x∗ is the book's standing assumption (p. 242). The fact ∇f(x∗)=0\nabla f(x^*)=0∇f(x∗)=0 used on the page is not a hypothesis; it follows from minimality. 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, display on p. 269 (Bubeck, arXiv:1405.4980v2): for gradient descent with
`η = 1/β` on a convex β-smooth `f` (β > 0) with a minimizer `x*`, for every `s ≥ 1`,
`‖x_{s+1} − x*‖² ≤ ‖x_s − x*‖² − (1/β²)‖∇f(x_s)‖²` and hence `‖x_{s+1} − x*‖ ≤ ‖x_s − x*‖`. -/
theorem thm_3_3_dist_decrease {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) :
    ‖x (s + 1) - xstar‖ ^ 2 ≤ ‖x s - xstar‖ ^ 2 - 1 / β ^ 2 * ‖g (x s)‖ ^ 2 ∧
      ‖x (s + 1) - xstar‖ ≤ ‖x s - xstar‖ := by sorry

end ConvexOptAlg.SmoothGD
Source
Bubeck, arXiv:1405.4980v2, §3.2, proof of Theorem 3.3, display on p. 269 (after (3.6))
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