Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eq. (3.5), p. 267 — a gradient step of length 1/β decreases f by at least ‖∇f(x)‖²/(2β)

Proved
ConvexOptAlg.SmoothGD.eq_3_5

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

convex-optimizationgradient-descentp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1smoothness

Let f:Rn→Rf:\mathbb R^n\to\mathbb Rf:Rn→R be convex and β\betaβ-smooth with β>0\beta>0β>0. Then for every x∈Rnx\in\mathbb R^nx∈Rn,

f(x−1β∇f(x))−f(x)≤−12β∥∇f(x)∥2.f\Bigl(x-\frac1\beta\nabla f(x)\Bigr)-f(x)\le-\frac{1}{2\beta}\|\nabla f(x)\|^2.f(x−β1​∇f(x))−f(x)≤−2β1​∥∇f(x)∥2.

This inequality measures the improvement made by one step of gradient descent with step size 1/β1/\beta1/β, and is the starting point of the analysis of Theorem 3.3.

Formalization Note Convexity is retained from the source context preceding (3.4). The condition β>0\beta>0β>0 is implicit in the page, which divides by β\betaβ.

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

/-- Eq. (3.5) (Bubeck, arXiv:1405.4980v2, p. 267): one gradient step of length `1/β` on a
convex β-smooth `f` (β > 0) decreases `f` by at least `‖∇f(x)‖²/(2β)`:
`f(x − (1/β)∇f(x)) − f(x) ≤ −(1/(2β))‖∇f(x)‖²`. -/
theorem eq_3_5 {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)
    (x : EuclideanSpace ℝ (Fin n)) :
    f (x - (1 / β) • g x) - f x ≤ -(1 / (2 * β)) * ‖g x‖ ^ 2 := by sorry

end ConvexOptAlg.SmoothGD
Source
Bubeck, arXiv:1405.4980v2, Eq. (3.5), 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