Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 1 (𝓗 part), p. 13; B.1, p. 38 — P(‖X⊤ϵ‖_∞ ≤ σ√(2 log 2p) + σ√(2 log(1/δ₀))) ≥ 1 − δ₀

Proved
SubsetShrink.Events.prob_H

by mikedeng1 · Oct 15, 2026 · Mathlib 0df444a (Lean v4.33.1)

gaussian-noisehigh-probability-eventsp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1sparse-regression

Let p≥1p\ge1p≥1, let X∈Rn×pX\in\mathbb R^{n\times p}X∈Rn×p have columns of unit Euclidean norm, let σ>0\sigma>0σ>0 and δ0∈(0,1]\delta_0\in(0,1]δ0​∈(0,1], and let ϵ\epsilonϵ have independent N(0,σ2)N(0,\sigma^2)N(0,σ2) coordinates. Then the event

H={∥X⊤ϵ∥∞≤σ2log⁡(2p)+σ2log⁡(1/δ0)}\mathcal H = \bigl\{\|X^\top\epsilon\|_\infty \le \sigma\sqrt{2\log(2p)}+\sigma\sqrt{2\log(1/\delta_0)}\bigr\}H={∥X⊤ϵ∥∞​≤σ2log(2p)​+σ2log(1/δ0​)​}

is measurable and

P(H)≥1−δ0.\mathbb P(\mathcal H)\ge1-\delta_0 .P(H)≥1−δ0​.

This is the maximal inequality for the ppp Gaussian variables Xj⊤ϵ∼N(0,σ2)X_j^\top\epsilon\sim N(0,\sigma^2)Xj⊤​ϵ∼N(0,σ2); it is used for the ℓ1\ell_1ℓ1​-regularized estimator (Theorem 3).

Formalization Note ∥X⊤ϵ∥∞\|X^\top\epsilon\|_\infty∥X⊤ϵ∥∞​ is the explicit maximum of ∣∑iXijϵi∣|\sum_i X_{ij}\epsilon_i|∣∑i​Xij​ϵi​∣ over jjj. The probability space is Rn\mathbb R^nRn with the law N(0,σ2)⊗nN(0,\sigma^2)^{\otimes n}N(0,σ2)⊗n. The hypothesis p≥1p\ge1p≥1 is the "s∈[p]s\in[p]s∈[p]" of Theorem 1.

Preamble
import Mathlib
import Definitions.Def_SubsetShrink_Events_Model

open MeasureTheory ProbabilityTheory
Formal statement
namespace SubsetShrink.Events
theorem prob_H {n p : ℕ} (hp : 1 ≤ p) (X : Matrix (Fin n) (Fin p) ℝ) (hX : UnitCols X)
    (σ : ℝ) (hσ : 0 < σ) (δ0 : ℝ) (hδ0 : 0 < δ0) (hδ1 : δ0 ≤ 1) :
    MeasurableSet (H X σ δ0) ∧ 1 - δ0 ≤ (noiseLaw n σ (H X σ δ0)).toReal := by sorry
end SubsetShrink.Events
Source
Mazumder, Radchenko & Dedieu, Subset Selection with Shrinkage, arXiv:1708.03288v4, p. 13, Theorem 1 (P(H) ≥ 1 − δ0); proof B.1, p. 38
Human review
  • Endorsed by Shuze Chen · Oct 15, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 15, 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