Prove2Me
Navigate
DiscoverCollectionsFormalpediaBlogsUsersMomentumMy Missions+
Prove2Me
⌕
Log in
← Formalpedia

(A.1), p. 21 — (1/2L)‖∇f(x) − ∇f(x⋆)‖² ≤ f(x) − f(x⋆) at a minimizer x⋆ of an L-smooth f

Proved
SGDKaczmarz.SGD.eq_A_1

by mikedeng1 · Oct 9, 2026 · Mathlib 0df444a (Lean v4.33.1)

gradient-lipschitzp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1smoothness

Let H\mathcal HH be a real Hilbert space and f:H→Rf : \mathcal H \to \mathbb Rf:H→R a differentiable function whose gradient is Lipschitz with constant L>0L > 0L>0:

∥∇f(x)−∇f(y)∥2≤L∥x−y∥2for all x,y.\|\nabla f(x) - \nabla f(y)\|_2 \le L\|x - y\|_2 \quad \text{for all } x, y.∥∇f(x)−∇f(y)∥2​≤L∥x−y∥2​for all x,y.

If x⋆x_\starx⋆​ is a global minimizer of fff, then for every x∈Hx \in \mathcal Hx∈H

12L∥∇f(x)−∇f(x⋆)∥22≤f(x)−f(x⋆).\frac{1}{2L}\|\nabla f(x) - \nabla f(x_\star)\|_2^2 \le f(x) - f(x_\star).2L1​∥∇f(x)−∇f(x⋆​)∥22​≤f(x)−f(x⋆​).

This is inequality (A.1) of the paper, which the proof of the co-coercivity Lemma A.1 applies to two auxiliary convex functions.

Formalization Note The page writes (A.1) as a chain whose middle term adds ⟨x−x⋆,∇f(x⋆)⟩\langle x - x_\star, \nabla f(x_\star)\rangle⟨x−x⋆​,∇f(x⋆​)⟩, which is 000 at a minimizer; only the outer inequality is stated. The hypothesis L>0L > 0L>0 is needed because the page divides by LLL. Convexity is not assumed: the inequality holds at any global minimizer.

Preamble
import Mathlib

open scoped NNReal InnerProductSpace
Formal statement
namespace SGDKaczmarz.SGD

/-- (A.1), proof of Lemma A.1, p. 21 (outer inequality): if `∇f` is `L`-Lipschitz and `x⋆`
minimizes `f`, then `(1/2L)‖∇f(x) − ∇f(x⋆)‖² ≤ f(x) − f(x⋆)`. -/
theorem eq_A_1 {H : Type*} [NormedAddCommGroup H] [InnerProductSpace ℝ H] [CompleteSpace H]
    (f : H → ℝ) (hf : Differentiable ℝ f) (L : ℝ≥0) (hL0 : 0 < L)
    (hL : LipschitzWith L (gradient f)) (xstar : H) (hmin : ∀ y, f xstar ≤ f y) (x : H) :
    1 / (2 * (L : ℝ)) * ‖gradient f x - gradient f xstar‖ ^ 2 ≤ f x - f xstar := by sorry

end SGDKaczmarz.SGD
Source
Needell, Srebro & Ward, Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm, arXiv:1310.5715v5, proof of Lemma A.1 (Appendix A.1), (A.1), p. 21
Human review
  • Endorsed by Shuze Chen · Oct 9, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 9, 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