Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 3.3, p. 267 — gradient descent with η = 1/β on a convex β-smooth f satisfies f(x_t) − f(x*) ≤ 2β‖x₁ − x*‖²/(t − 1)

Proved
ConvexOptAlg.SmoothGD.theorem_3_3

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

convergence-rateconvex-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 (xt)t≥1(x_t)_{t\ge1}(xt​)t≥1​ be gradient descent with step size η=1/β\eta=1/\betaη=1/β started at x1x_1x1​:

xt+1=xt−1β∇f(xt).x_{t+1}=x_t-\frac1\beta\nabla f(x_t).xt+1​=xt​−β1​∇f(xt​).

Then for every t≥2t\ge2t≥2,

f(xt)−f(x∗)≤2β∥x1−x∗∥2t−1.f(x_t)-f(x^*)\le\frac{2\beta\|x_1-x^*\|^2}{t-1}.f(xt​)−f(x∗)≤t−12β∥x1​−x∗∥2​.

This is the basic convergence rate of gradient descent on smooth convex functions: the optimality gap decays like 1/t1/t1/t, with a constant depending only on the smoothness and on the initial distance to a minimizer, and not on the dimension.

Formalization Note The bound is stated for t≥2t\ge2t≥2: at t=1t=1t=1 the right-hand side has denominator 000. The existence of a minimizer x∗x^*x∗ is the book's standing assumption (p. 242). β>0\beta>0β>0 is implicit in the step size η=1/β\eta=1/\betaη=1/β. The gradient is an explicit map ggg with g(x)=∇f(x)g(x)=\nabla f(x)g(x)=∇f(x), and Rn\mathbb R^nRn is EuclideanSpace ℝ (Fin n).

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

/-- Theorem 3.3 (Bubeck, arXiv:1405.4980v2, p. 267): let `f` be convex and β-smooth on `ℝⁿ`
(β > 0) with a minimizer `x*`. Then gradient descent with `η = 1/β`, started at `x₁`, satisfies
`f(x_t) − f(x*) ≤ 2β‖x₁ − x*‖²/(t − 1)` for every `t ≥ 2`. -/
theorem theorem_3_3 {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) (t : ℕ) (ht : 2 ≤ t) :
    f (x t) - f xstar ≤ 2 * β * ‖x 1 - xstar‖ ^ 2 / ((t : ℝ) - 1) := by sorry

end ConvexOptAlg.SmoothGD
Source
Bubeck, arXiv:1405.4980v2, Theorem 3.3, p. 267
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