Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Corollary 3, p. 67 — a σ-sub-Gaussian variable satisfies (209) and hence (210)

Proved
InfoRelaxTS.Gap.corollary_3

by mikedeng1 · Oct 13, 2026 · Mathlib 0df444a (Lean v4.33.1)

concentrationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1probabilitysub-gaussian

Let XXX be a real random variable on a probability space and σ>0\sigma>0σ>0. Suppose XXX is σ\sigmaσ-sub-Gaussian with variance proxy σ2\sigma^2σ2:

E[exp⁡(λ(X−EX))]≤exp⁡(σ2λ22)for all λ∈R.\mathbb E\big[\exp(\lambda(X-\mathbb EX))\big]\le\exp\Big(\frac{\sigma^2\lambda^2}{2}\Big)\qquad\text{for all }\lambda\in\mathbb R .E[exp(λ(X−EX))]≤exp(2σ2λ2​)for all λ∈R.

Then XXX satisfies the tail condition of Lemma 4,

P[X≥EX+zσ]≤e−z2/2(z≥0),\mathbb P\big[X\ge\mathbb EX+z\sigma\big]\le e^{-z^2/2}\quad(z\ge0),P[X≥EX+zσ]≤e−z2/2(z≥0),

and hence

E[(X−(EX+zσ))+]≤σz e−z2/2(z>0).\mathbb E\Big[\big(X-(\mathbb EX+z\sigma)\big)^+\Big]\le\frac{\sigma}{z}\,e^{-z^2/2}\quad(z>0).E[(X−(EX+zσ))+]≤zσ​e−z2/2(z>0).

This is the form in which Lemma 4 is used for the sub-Gaussian mean-reward metrics of Lemma 5.

Formalization Note Definition 3 (p. 66) prints the bound exp⁡(σλ2/2)\exp(\sigma\lambda^2/2)exp(σλ2/2); every use in the paper ((213), (214) with σ=L/ν\sigma=\sqrt{L/\nu}σ=L/ν​, (236)) has σ2\sigma^2σ2, and with the printed form the corollary would fail for σ<1\sigma<1σ<1. The statement uses Mathlib's HasSubgaussianMGF for X−EXX-\mathbb EXX−EX with parameter σ2\sigma^2σ2, which also records that eλ(X−EX)e^{\lambda(X-\mathbb EX)}eλ(X−EX) is integrable for every λ\lambdaλ.

Preamble
import Mathlib

open MeasureTheory ProbabilityTheory
Formal statement
namespace InfoRelaxTS.Gap

theorem corollary_3 {Ω : Type*} [MeasurableSpace Ω] (μ : Measure Ω) [IsProbabilityMeasure μ]
    (X : Ω → ℝ) (σ : ℝ) (hσ : 0 < σ)
    (hX : HasSubgaussianMGF (fun ω => X ω - ∫ x, X x ∂μ) ⟨σ ^ 2, sq_nonneg σ⟩ μ) :
    (∀ z : ℝ, 0 ≤ z →
      (μ {ω | (∫ x, X x ∂μ) + z * σ ≤ X ω}).toReal ≤ Real.exp (-z ^ 2 / 2)) ∧
    (∀ z : ℝ, 0 < z →
      ∫ ω, max (X ω - ((∫ x, X x ∂μ) + z * σ)) 0 ∂μ ≤ σ / z * Real.exp (-z ^ 2 / 2)) := by sorry

end InfoRelaxTS.Gap
Source
Min, Maglaras, Moallemi, Thompson Sampling with Information Relaxation Penalties, arXiv:1902.04251v2, pp. 66–67, Definition 3 (208), Corollary 3
Human review
  • Endorsed by Shuze Chen · Oct 14, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 14, 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