Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Gaussian posterior overshoot at one exact realized rank

Proved
BanditAlgorithm.gaussian_exact_rank_posterior_overshoot_probability_bound

by Harry_Xu · Jul 31, 2026 · Mathlib c5ea003 (Lean v4.30.0)

banditsconcentrationgaussianthompson-sampling

Fix an optimal arm i0i_0i0​, a suboptimal arm iii of gap Δi>0\Delta_i>0Δi​>0, a separating offset 0<ε<Δi0<\varepsilon<\Delta_i0<ε<Δi​, a horizon n≥2n\ge2n≥2, and a positive exact realized rank sss. On histories where arm iii has been pulled more than sss times, the probability that its rank-sss Gaussian posterior assigns more than 1/n1/n1/n mass above μ∗−ε\mu_* - \varepsilonμ∗​−ε is at most

{exp⁡ ⁣[−s(Δi−ε−2log⁡(n)/s)22],2log⁡n(Δi−ε)2<s,1,otherwise.\begin{cases} \exp\!\left[-\dfrac{s\left(\Delta_i-\varepsilon-\sqrt{2\log(n)/s}\right)^2}{2}\right],&\dfrac{2\log n}{(\Delta_i-\varepsilon)^2}<s,\\ 1,&\text{otherwise.} \end{cases}⎩⎨⎧​exp​−2s(Δi​−ε−2log(n)/s​)2​​,1,​(Δi​−ε)22logn​<s,otherwise.​

This is the arbitrary-threshold exact-rank form of the deviation estimate used in Exercise 36.6(b).

Preamble
import Definitions.Def_ThompsonSampling
import Definitions.Def_GaussianBandit

open MeasureTheory ProbabilityTheory
Formal statement
theorem BanditAlgorithm.gaussian_exact_rank_posterior_overshoot_probability_bound :
    ∀ (k : ℕ) [NeZero k] (μvec : Fin k → ℝ) (π : BanditAlgorithm.BanditPolicy k),
      ∀ (i₀ : Fin k),
        BanditAlgorithm.banditArmMean (BanditAlgorithm.gaussianBandit μvec) i₀ =
          BanditAlgorithm.banditOptimalMean (BanditAlgorithm.gaussianBandit μvec) →
      ∀ (i : Fin k), 0 < BanditAlgorithm.banditGap (BanditAlgorithm.gaussianBandit μvec) i →
      ∀ ε : ℝ, 0 < ε →
        ε < BanditAlgorithm.banditGap (BanditAlgorithm.gaussianBandit μvec) i →
      ∀ n : ℕ, 2 ≤ n →
      ∀ s : ℕ, 0 < s →
        (BanditAlgorithm.banditMeasure (BanditAlgorithm.gaussianBandit μvec) π n).real
          {h : BanditAlgorithm.BanditHistory k n |
            s < BanditAlgorithm.armPullCount i h ∧
              1 / (n : ℝ) <
                BanditAlgorithm.gaussianTSTailProb i s
                  (BanditAlgorithm.banditArmMean (BanditAlgorithm.gaussianBandit μvec) i₀ - ε) h} ≤
          if 2 * Real.log n /
                (BanditAlgorithm.banditGap (BanditAlgorithm.gaussianBandit μvec) i - ε) ^ 2 < (s : ℝ)
          then
            Real.exp
              (-((s : ℝ) *
                (BanditAlgorithm.banditGap (BanditAlgorithm.gaussianBandit μvec) i - ε -
                  Real.sqrt (2 * Real.log n / s))) ^ 2 /
                ((2 : ℝ) * (s : ℝ) * 1))
          else 1 := by sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (CUP 2020), Exercise 36.6(b), printed p. 475 / PDF p. 484; Theorem 36.2 and Eq. (36.3), printed pp. 463–465 / PDF pp. 472–474; reward-stack construction in §4.6, printed p. 65 / PDF p. 74.

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