Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 7.49, p. 131 — stability of regularized linear minimizers

Proved
ModernOnlineLearning.FTRL.lemma_7_49

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

ftrlonline-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1stability

Let ψ\psiψ be λ\lambdaλ-strongly convex on a nonempty, closed and convex feasible set VVV, where λ>0\lambda>0λ>0. For dual vectors θ(1)\theta^{(1)}θ(1) and θ(2)\theta^{(2)}θ(2), let x(j)x^{(j)}x(j) minimize ψ(z)+θ(j)(z)\psi(z)+\theta^{(j)}(z)ψ(z)+θ(j)(z) over VVV. Then

∥x(1)−x(2)∥≤∥θ(1)−θ(2)∥∗λ.\|x^{(1)}-x^{(2)}\|\le\frac{\|\theta^{(1)}-\theta^{(2)}\|_*}{\lambda}.∥x(1)−x(2)∥≤λ∥θ(1)−θ(2)∥∗​​.

The lemma controls how much a regularized linear prediction can change when its linear term changes.

Formalization Note The two minimizers are supplied rather than selected by a choice operator. Dual vectors are continuous linear functionals, and their operator norm is ∥⋅∥∗\|\cdot\|_*∥⋅∥∗​.

Preamble
import Mathlib
import Definitions.Def_ModernOnlineLearning_FTRL_Defs

set_option autoImplicit false
Formal statement
namespace ModernOnlineLearning.FTRL

/-- Orabona, Lemma 7.49, p. 131: sensitivity of a regularized linear minimizer. -/
theorem lemma_7_49
    {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E]
    (V : Set E) (hVclosed : IsClosed V) (hVconvex : Convex ℝ V)
    (hVnonempty : V.Nonempty) (ψ : E → ℝ)
    (lam : ℝ) (hlam : 0 < lam) (hStrong : StrongConvexOn V lam ψ)
    (θ₁ θ₂ : E →L[ℝ] ℝ) (x₁ x₂ : E)
    (hx₁ : IsMinimizerOn V (fun z => ψ z + θ₁ z) x₁)
    (hx₂ : IsMinimizerOn V (fun z => ψ z + θ₂ z) x₂) :
    ‖x₁ - x₂‖ ≤ (1 / lam) * ‖θ₁ - θ₂‖ := by sorry

end ModernOnlineLearning.FTRL
Source
Orabona, arXiv:1912.13213v10, Lemma 7.49, p. 131
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 paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me