Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Means, gaps and optimal arms of a Gaussian bandit

Proved
BanditAlgorithm.gaussianBandit_mean_gap_dictionary

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

banditsgaussian

The dictionary between the Gaussian bandit ν=N(μ1,1)⊗⋯⊗N(μk,1)\nu=\mathcal N(\mu_1,1)\otimes\cdots\otimes\mathcal N(\mu_k,1)ν=N(μ1​,1)⊗⋯⊗N(μk​,1) and its parameter vector μ∈Rk\mu\in\mathbb R^kμ∈Rk: the arm means of ν\nuν are μi\mu_iμi​, the suboptimality gaps are

Δi=max⁡jμj−μi,\Delta_i=\max_j\mu_j-\mu_i,Δi​=jmax​μj​−μi​,

and arm iii is suboptimal (Δi>0\Delta_i>0Δi​>0) exactly when some other arm has a strictly larger parameter.

Every statement about the Gaussian class ENk(1)\mathcal E^k_{\mathcal N}(1)ENk​(1) is phrased through μ\muμ, while the general framework of Chapter 33 is phrased through the abstract means and gaps of a StochasticBandit. This lemma is the translation between the two, and is used at essentially every step of the Track-and-Stop analysis.

Preamble
import Definitions.Def_TrackAndStop
import Definitions.Def_GaussianBandit

open MeasureTheory ProbabilityTheory InformationTheory NNReal ENNReal
Formal statement
theorem BanditAlgorithm.gaussianBandit_mean_gap_dictionary {k : ℕ} [NeZero k]
    (μvec : Fin k → ℝ) (i : Fin k) :
    BanditAlgorithm.banditArmMean (BanditAlgorithm.gaussianBandit μvec) i = μvec i ∧
      BanditAlgorithm.banditGap (BanditAlgorithm.gaussianBandit μvec) i
          = (⨆ j, μvec j) - μvec i ∧
        (0 < BanditAlgorithm.banditGap (BanditAlgorithm.gaussianBandit μvec) i
          ↔ ∃ j, μvec i < μvec j) ∧
          (i ∈ BanditAlgorithm.banditOptimalArms (BanditAlgorithm.gaussianBandit μvec)
            ↔ ∀ j, μvec j ≤ μvec i) := by
  sorry
Source
Lattimore & Szepesvari, Bandit Algorithms (CUP 2020), Sections 4.4, 4.5 and 33.1.

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