Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

BanditAlgorithm.subgaussian_sample_mean_tail_bound

Proved

by Shuze Chen · Jul 17, 2026 · Mathlib 0df444a (Lean v4.33.1)

banditsconcentrationhoeffdingprobability

(Hoeffding-type bound, GOAL — L&S Corollary 5.5) Assume Xi−μX_i - \muXi​−μ are independent, σ\sigmaσ-subgaussian random variables for i=1,…,ni = 1, \dots, ni=1,…,n (with σ>0\sigma > 0σ>0), and let

μ^=1n∑t=1nXt\hat\mu = \frac{1}{n}\sum_{t=1}^n X_tμ^​=n1​t=1∑n​Xt​

be the sample mean. Then for any ε≥0\varepsilon \ge 0ε≥0,

P(μ^≥μ+ε)≤exp⁡ ⁣(−nε22σ2)andP(μ^≤μ−ε)≤exp⁡ ⁣(−nε22σ2).\mathbb{P}(\hat\mu \ge \mu + \varepsilon) \le \exp\!\left(-\frac{n\varepsilon^2}{2\sigma^2}\right) \quad\text{and}\quad \mathbb{P}(\hat\mu \le \mu - \varepsilon) \le \exp\!\left(-\frac{n\varepsilon^2}{2\sigma^2}\right).P(μ^​≥μ+ε)≤exp(−2σ2nε2​)andP(μ^​≤μ−ε)≤exp(−2σ2nε2​).

(Here σ\sigmaσ-subgaussian means Mathlib's HasSubgaussianMGF with variance proxy σ2\sigma^2σ2.)

Preamble
import Mathlib.Probability.Moments.SubGaussian

open MeasureTheory ProbabilityTheory Real NNReal
Formal statement
theorem BanditAlgorithm.subgaussian_sample_mean_tail_bound
    {Ω : Type} {mΩ : MeasurableSpace Ω} {P : Measure Ω} [IsProbabilityMeasure P]
    {n : ℕ} (hn : 0 < n) {X : Fin n → Ω → ℝ} {m : ℝ} {σ : ℝ≥0} (hσ : 0 < σ)
    (h_indep : iIndepFun (fun i ω ↦ X i ω - m) P)
    (h_subG : ∀ i, HasSubgaussianMGF (fun ω ↦ X i ω - m) (σ ^ 2) P)
    {ε : ℝ} (hε : 0 ≤ ε) :
    P.real {ω | m + ε ≤ (∑ i, X i ω) / n} ≤
        exp (-((n : ℝ) * ε ^ 2) / (2 * (σ : ℝ) ^ 2)) ∧
    P.real {ω | (∑ i, X i ω) / n ≤ m - ε} ≤
        exp (-((n : ℝ) * ε ^ 2) / (2 * (σ : ℝ) ^ 2)) := by
  sorry
Source
L&S Corollary 5.5, p.78
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).

  • Endorsed by iris · Oct 31, 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