Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(51), p. 49 — basic inequality for the BIC-type estimator β̂^B_2

Proved
SubsetShrink.BIC.eq_51

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

best-subset-selectionmodel-selectionoracle-inequalityp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1sparse-regression

Let X∈Rn×pX\in\mathbb R^{n\times p}X∈Rn×p, f∗,ϵ∈Rnf^*,\epsilon\in\mathbb R^nf∗,ϵ∈Rn, y=f∗+ϵy=f^*+\epsilony=f∗+ϵ and a,b∈Ra,b\in\mathbb Ra,b∈R. Let β^\hat\betaβ^​ be any global minimizer over Rp\mathbb R^pRp of ∥y−Xβ∥2+λβ∥β∥+μβ∥β∥0\|y-X\beta\|^2+\lambda_\beta\|\beta\|+\mu_\beta\|\beta\|_0∥y−Xβ∥2+λβ​∥β∥+μβ​∥β∥0​, where λβ=a∥β∥0log⁡(ep/∥β∥0)\lambda_\beta=a\sqrt{\|\beta\|_0\log(ep/\|\beta\|_0)}λβ​=a∥β∥0​log(ep/∥β∥0​)​ and μβ=blog⁡(ep/∥β∥0)\mu_\beta=b\log(ep/\|\beta\|_0)μβ​=blog(ep/∥β∥0​). Then for every β∈Rp\beta\in\mathbb R^pβ∈Rp,

∥f∗−Xβ^∥2+λβ^∥β^∥+μβ^∥β^∥0≤∥f∗−Xβ∥2+2ϵ⊤X(β^−β)+λβ∥β∥+μβ∥β∥0.\|f^*-X\hat\beta\|^2+\lambda_{\hat\beta}\|\hat\beta\|+\mu_{\hat\beta}\|\hat\beta\|_0\le\|f^*-X\beta\|^2+2\epsilon^\top X(\hat\beta-\beta)+\lambda_\beta\|\beta\|+\mu_\beta\|\beta\|_0 .∥f∗−Xβ^​∥2+λβ^​​∥β^​∥+μβ^​​∥β^​∥0​≤∥f∗−Xβ∥2+2ϵ⊤X(β^​−β)+λβ​∥β∥+μβ​∥β∥0​.

This deterministic inequality is the starting point of every bound for β^2B\hat\beta^B_2β^​2B​: the remaining work is to control the noise term 2ϵ⊤X(β^−β)2\epsilon^\top X(\hat\beta-\beta)2ϵ⊤X(β^​−β) on high-probability events.

Formalization Note The statement is deterministic: ϵ\epsilonϵ is an arbitrary vector and no distributional assumption is used. Products μβ∥β∥0\mu_\beta\|\beta\|_0μβ​∥β∥0​ are muB b β * l0 β (value 000 at β=0\beta=0β=0).

Preamble
import Mathlib
import Definitions.Def_SubsetShrink_BIC_Model
Formal statement
namespace SubsetShrink.BIC

open MeasureTheory ProbabilityTheory

/-- (51), p. 49: the basic inequality for a minimizer of the objective of `β̂^B_2`. -/
theorem eq_51 {n p : ℕ} (X : Matrix (Fin n) (Fin p) ℝ) (fstar ε : Fin n → ℝ) (a b : ℝ)
    (βhat : Fin p → ℝ) (hβhat : IsBIC2 X (fstar + ε) a b βhat) (β : Fin p → ℝ) :
    ∑ i, (fstar i - X.mulVec βhat i) ^ 2 + lamB a βhat * SubsetShrink.Events.l2 βhat + muB b βhat * (SubsetShrink.Events.l0 βhat : ℝ) ≤
      ∑ i, (fstar i - X.mulVec β i) ^ 2 + 2 * SubsetShrink.Events.dot ε (X.mulVec (βhat - β)) +
        lamB a β * SubsetShrink.Events.l2 β + muB b β * (SubsetShrink.Events.l0 β : ℝ) := by sorry

end SubsetShrink.BIC
Source
Mazumder, Radchenko & Dedieu, Subset Selection with Shrinkage, arXiv:1708.03288v4, p. 49, proof of Theorem 5 (B.13), (51)
Human review
  • Endorsed by Shuze Chen · Oct 16, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 16, 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