Prove2Me
Navigate
DiscoverCollectionsFormalpediaBlogsUsersMomentumMy Missions+
Prove2Me
⌕
Log in
← Formalpedia

Eq. (3.19) — suboptimality bounded by the squared gradient norm

Proved
StochQuasiNewton.SQN.suboptimality_le_gradient_sq

by mikedeng1 · Sep 27, 2026 · Mathlib 0df444a (Lean v4.33.1)

convex-optimizationp2o-batch-p200bp2o-gran-per-chapterp2o-plan-paperp2o-v1strong-convexity

Let F:Rn→RF:\mathbb R^n\to\mathbb RF:Rn→R be C2C^2C2 and suppose ∇2F(w)≻λI\nabla^2F(w)\succ\lambda I∇2F(w)≻λI for every www, with λ>0\lambda>0λ>0 (the lower bound in (3.4)). Then for all v,w∈Rnv,w\in\mathbb R^nv,w∈Rn,

F(v)≥F(w)−12λ∥∇F(w)∥2,F(v)\ge F(w)-\frac1{2\lambda}\|\nabla F(w)\|^2,F(v)≥F(w)−2λ1​∥∇F(w)∥2,

and if w∗w^*w∗ minimizes FFF, then for every www

2λ [F(w)−F(w∗)]≤∥∇F(w)∥2.2\lambda\,[F(w)-F(w^*)]\le\|\nabla F(w)\|^2 .2λ[F(w)−F(w∗)]≤∥∇F(w)∥2.

This inequality converts the gradient term of the descent inequality (3.18) into a suboptimality term, yielding the recursion (3.22).

Formalization Note Only the lower Hessian bound is assumed, as in the paper's derivation. A published Boyd–Vandenberghe statement of the same inequality exists on the platform in the older Mathlib environment c5ea003; it cannot be imported from this mission's environment, so the inequality is restated here.

Preamble
import Mathlib

open scoped RealInnerProductSpace
Formal statement
namespace StochQuasiNewton.SQN

/-- Eq. (3.19) and the line after it: if `F` is `C²` with `∇²F(w) ≻ λ I` for every `w` (the
lower bound of (3.4)), then `F(v) ≥ F(w) − ‖∇F(w)‖² / (2λ)` for all `v, w`, and for a minimizer
`w*` of `F`, `2λ [F(w) − F(w*)] ≤ ‖∇F(w)‖²` for every `w`. -/
theorem suboptimality_le_gradient_sq {n : ℕ} (F : EuclideanSpace ℝ (Fin n) → ℝ)
    (hF : ContDiff ℝ 2 F) (lam : ℝ) (hlam : 0 < lam)
    (hHess : ∀ w v : EuclideanSpace ℝ (Fin n), v ≠ 0 →
      lam * ‖v‖ ^ 2 < ⟪fderiv ℝ (gradient F) w v, v⟫)
    (wstar : EuclideanSpace ℝ (Fin n)) (hwstar : IsMinOn F Set.univ wstar) :
    (∀ w v : EuclideanSpace ℝ (Fin n), F w - 1 / (2 * lam) * ‖gradient F w‖ ^ 2 ≤ F v) ∧
      ∀ w : EuclideanSpace ℝ (Fin n), 2 * lam * (F w - F wstar) ≤ ‖gradient F w‖ ^ 2 := by sorry

end StochQuasiNewton.SQN
Source
Byrd, Hansen, Nocedal, Singer, A Stochastic Quasi-Newton Method for Large-Scale Optimization, SIAM J. Optim. 26(2) (2016), p. 1017, Eq. (3.19) and the displayed inequality after it
Human review
  • Endorsed by Shuze Chen · Oct 1, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 1, 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 paper
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me