Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Corollary 3 (B.5), p. 42 — from W ≤ κ log(1/δ0) w.p. 1 − δ0/2 to E W ≤ κ/2

Proved
SubsetShrink.BIC.tail_to_expectation

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

expectationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1probabilitytail-bound

Let (Ω,F,P)(\Omega,\mathcal F,P)(Ω,F,P) be a probability space, W:Ω→RW:\Omega\to\mathbb RW:Ω→R a random variable and κ>0\kappa>0κ>0. Suppose that for every δ0∈(0,1)\delta_0\in(0,1)δ0​∈(0,1),

P(W≤κlog⁡(1/δ0))≥1−δ0/2.P\big(W\le\kappa\log(1/\delta_0)\big)\ge1-\delta_0/2 .P(W≤κlog(1/δ0​))≥1−δ0​/2.

Then 2P(W>w)≤e−w/κ2P(W>w)\le e^{-w/\kappa}2P(W>w)≤e−w/κ for every w≥0w\ge0w≥0, and

E W+=Emax⁡(W,0)≤∫0∞P(W>w) dw≤12∫0∞e−w/κ dw=κ2.\mathbb E\,W^+=\mathbb E\max(W,0)\le\int_0^\infty P(W>w)\,dw\le\tfrac12\int_0^\infty e^{-w/\kappa}\,dw=\frac{\kappa}{2}.EW+=Emax(W,0)≤∫0∞​P(W>w)dw≤21​∫0∞​e−w/κdw=2κ​.

The proof of Theorem 5 applies this with κ\kappaκ a universal multiple of σ2\sigma^2σ2 and WWW the excess of ∥f∗−Xβ^∥2\|f^*-X\hat\beta\|^2∥f∗−Xβ^​∥2 over CCC times the oracle term, turning the high-probability bounds (56) and (58) into the expectation bounds of Theorem 5.

Formalization Note The page writes EW\mathbb EWEW but bounds it through P(W>w)P(W>w)P(W>w) for w≥0w\ge0w≥0 only, which is a bound on EW+\mathbb E W^+EW+; the statement's lower Lebesgue integral of max⁡(W,0)\max(W,0)max(W,0) (∫⁻ ofReal W) is exactly EW+\mathbb E W^+EW+, and it bounds EW\mathbb EWEW whenever the latter is defined. In the paper κ=c0σ2\kappa=c_0\sigma^2κ=c0​σ2.

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

open MeasureTheory ProbabilityTheory

/-- Proof of Corollary 3 (B.5), p. 42: if `W ≤ κ log(1/δ0)` with probability at least `1 − δ0/2`
for every `δ0 ∈ (0, 1)`, then `2 P(W > w) ≤ e^{−w/κ}` for every `w ≥ 0`, and
`E[W⁺] ≤ κ/2` (here `κ = c0 σ²`). -/
theorem tail_to_expectation {Ω : Type*} [MeasurableSpace Ω] (μ : Measure Ω)
    [IsProbabilityMeasure μ] (W : Ω → ℝ) (hW : Measurable W) (κ : ℝ) (hκ : 0 < κ)
    (h : ∀ δ0 : ℝ, 0 < δ0 → δ0 < 1 →
      1 - δ0 / 2 ≤ (μ {ω | W ω ≤ κ * Real.log (1 / δ0)}).toReal) :
    (∀ w : ℝ, 0 ≤ w → 2 * (μ {ω | w < W ω}).toReal ≤ Real.exp (-w / κ)) ∧
    ∫⁻ ω, ENNReal.ofReal (W ω) ∂μ ≤ ENNReal.ofReal (κ / 2) := by sorry

end SubsetShrink.BIC
Source
Mazumder, Radchenko & Dedieu, Subset Selection with Shrinkage, arXiv:1708.03288v4, p. 42, proof of Corollary 3 (B.5), displays 2P(W > w) ≤ e^{−w/[c0σ²]} and EW ≤ … ≤ c0σ²/2; invoked in B.13, p. 50
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