Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§3.2, proof of Theorem 3.3, p. 269 — ωδ_s² + δ_{s+1} ≤ δ_s for all s ≥ 1 implies 1/δ_t ≥ ω(t − 1)

Proved
ConvexOptAlg.SmoothGD.thm_3_3_sequence_rate

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

convex-optimizationgradient-descentp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1sequences

Let (δs)s≥1(\delta_s)_{s\ge1}(δs​)s≥1​ be a sequence of non-negative reals and ω>0\omega>0ω>0, and suppose that for every s≥1s\ge1s≥1,

ω δs2+δs+1≤δs.\omega\,\delta_s^2+\delta_{s+1}\le\delta_s.ωδs2​+δs+1​≤δs​.

Then for every t≥2t\ge2t≥2,

ω (t−1) δt≤1,\omega\,(t-1)\,\delta_t\le 1,ω(t−1)δt​≤1,

i.e. 1/δt≥ω(t−1)1/\delta_t\ge\omega(t-1)1/δt​≥ω(t−1) whenever δt>0\delta_t>0δt​>0.

This is the purely numerical step of the proof of Theorem 3.3: applied with ω=1/(2β∥x1−x∗∥2)\omega=1/(2\beta\|x_1-x^*\|^2)ω=1/(2β∥x1​−x∗∥2) to the optimality gaps, it gives the rate δt≤2β∥x1−x∗∥2/(t−1)\delta_t\le 2\beta\|x_1-x^*\|^2/(t-1)δt​≤2β∥x1​−x∗∥2/(t−1).

Formalization Note The page divides by δs\delta_sδs​ and δs+1\delta_{s+1}δs+1​; the Lean conclusion is multiplied through by δt\delta_tδt​ so that it also covers δt=0\delta_t=0δt​=0. The page defines ω=1/(2β∥x1−x∗∥2)>0\omega=1/(2\beta\|x_1-x^*\|^2)>0ω=1/(2β∥x1​−x∗∥2)>0 in the nontrivial case; this lemma carries that positivity explicitly.

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

/-- Proof of Theorem 3.3, first display on p. 269 (Bubeck, arXiv:1405.4980v2), as a lemma on real
sequences: if `ω > 0`, `δ_s ≥ 0` and `ω δ_s² + δ_{s+1} ≤ δ_s` for every `s ≥ 1`, then for every `t ≥ 2`,
`ω (t − 1) δ_t ≤ 1`, i.e. `1/δ_t ≥ ω(t − 1)` whenever `δ_t > 0`. Stated without division so
that it also covers `δ_t = 0`. -/
theorem thm_3_3_sequence_rate (δ : ℕ → ℝ) (ω : ℝ) (hω : 0 < ω)
    (hδ : ∀ s : ℕ, 1 ≤ s → 0 ≤ δ s)
    (hrec : ∀ s : ℕ, 1 ≤ s → ω * δ s ^ 2 + δ (s + 1) ≤ δ s) (t : ℕ) (ht : 2 ≤ t) :
    ω * ((t : ℝ) - 1) * δ t ≤ 1 := by sorry

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