Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

BanditAlgorithm.bandit_subgaussian_maximal_inequality

Proved

by Shuze Chen · Jul 19, 2026 · Mathlib 0df444a (Lean v4.33.1)

concentrationmartingaleprobability

(Maximal concentration) Let X0,X1,…X_0, X_1, \dotsX0​,X1​,… be independent σ\sigmaσ-subgaussian (σ>0\sigma > 0σ>0) random variables and St=∑s<tXsS_t = \sum_{s<t} X_sSt​=∑s<t​Xs​. Then for any ε>0\varepsilon > 0ε>0 and n≥1n \ge 1n≥1,

P(∃ t∈[1,n]:St≥ε)≤exp⁡ ⁣(−ε22nσ2)\mathbb{P}\left(\exists\, t \in [1,n] : S_t \ge \varepsilon\right) \le \exp\!\left(-\frac{\varepsilon^2}{2n\sigma^2}\right)P(∃t∈[1,n]:St​≥ε)≤exp(−2nσ2ε2​)

(via Doob's submartingale inequality applied to exp⁡(λSt)\exp(\lambda S_t)exp(λSt​)).

Preamble
import Mathlib.Probability.Moments.SubGaussian


open MeasureTheory ProbabilityTheory Real NNReal
Formal statement
theorem BanditAlgorithm.bandit_subgaussian_maximal_inequality
    {Ω : Type} {mΩ : MeasurableSpace Ω} {P : Measure Ω} [IsProbabilityMeasure P]
    {X : ℕ → Ω → ℝ} {σ : ℝ≥0} (hσ : 0 < σ)
    (h_indep : iIndepFun X P)
    (h_subG : ∀ i, HasSubgaussianMGF (X i) (σ ^ 2) P)
    {n : ℕ} (hn : 0 < n) {ε : ℝ} (hε : 0 < ε) :
    P.real {ω | ∃ t, 0 < t ∧ t ≤ n ∧ ε ≤ ∑ s ∈ Finset.range t, X s ω} ≤
      exp (-ε ^ 2 / (2 * n * (σ : ℝ) ^ 2)) := by
  sorry
Source
L&S Theorem 9.2, p.125

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