Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§3, p. 6 — the prescribed gradients satisfy (2.3): ∥gk∥≥(1/(k+1))1/(2−τ)\|g_k\| \ge (1/(k+1))^{1/(2-\tau)}∥gk​∥≥(1/(k+1))1/(2−τ)

Proved
SlowConvergence.Newton.gradient_lower_bound

by mikedeng1 · Oct 8, 2026 · Mathlib 0df444a (Lean v4.33.1)

lower-boundp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1worst-case-complexity

Let 0<τ<10 < \tau < 10<τ<1, η=τ/(4−2τ)\eta = \tau/(4-2\tau)η=τ/(4−2τ), and let gk=−((1/(k+1))12+η,(1/(k+1))2)Tg_k = -\big((1/(k+1))^{\frac12+\eta}, (1/(k+1))^2\big)^Tgk​=−((1/(k+1))21​+η,(1/(k+1))2)T be the gradients prescribed by (3.4). Then 12+η=12−τ\tfrac12 + \eta = \tfrac1{2-\tau}21​+η=2−τ1​, and for every k≥0k \ge 0k≥0

∥gk∥  ≥  (1k+1)12−τ,\|g_k\| \;\ge\; \Big(\frac1{k+1}\Big)^{\frac1{2-\tau}} ,∥gk​∥≥(k+11​)2−τ1​,

which is the requirement (2.3).

This is the inequality that turns the construction into a complexity lower bound: an iterate with ∥gk∥≤ε\|g_k\| \le \varepsilon∥gk​∥≤ε can occur only once k+1≥ε−(2−τ)k+1 \ge \varepsilon^{-(2-\tau)}k+1≥ε−(2−τ).

Preamble
import Mathlib
import Definitions.Def_SlowConvergence_Newton_Data
import Definitions.Def_SlowConvergence_Newton_Pieces

open scoped RealInnerProductSpace
Formal statement
namespace SlowConvergence.Newton

/-- Cartis, Gould & Toint, preprint 15 Oct 2009, §3, p. 6, after (3.4): "The first part of (3.4) then
immediately gives (2.3) by construction, since the norm of that vector is at least equal to the absolute
value of its first component." With `η = τ/(4 − 2τ)` (2.10), `1/2 + η = 1/(2 − τ)`, and the prescribed
gradient `g_k` of (3.4) satisfies (2.3): `‖g_k‖ ≥ (1/(k+1))^{1/(2−τ)}` for all `k ≥ 0`. -/
theorem gradient_lower_bound (τ : ℝ) (hτ0 : 0 < τ) (hτ1 : τ < 1) :
    1 / 2 + eta τ = 1 / (2 - τ) ∧
      ∀ k : ℕ, (1 / ((k : ℝ) + 1)) ^ (1 / (2 - τ)) ≤ ‖gk τ k‖ := by sorry

end SlowConvergence.Newton
Source
Cartis, Gould & Toint, On the complexity of steepest descent, Newton's and regularized Newton's methods, preprint 15 Oct 2009, p. 6, §3, after (3.4); (2.3) and (2.10), p. 3
Human review
  • Endorsed by Shuze Chen · Oct 8, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 8, 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