Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 4, p. 14 — under the Greedy Bandit, ℙ[λ_min(Σ̂(S_{i,t})) ≥ λ₀t/4] ≥ 1 − exp(log d − C₁t), C₁ = λ₀/(40x²_max)

Proved
MostlyExplorationFree.GreedyBandit.lemma_4

by mikedeng1 · Oct 22, 2026 · Mathlib 0df444a (Lean v4.33.1)

contextual-banditcovariate-diversitygreedy-algorithmminimum-eigenvaluep2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Consider the Greedy Bandit run on the two-armed linear contextual bandit with d≥1d \ge 1d≥1, under the parameter-set assumption (contexts bounded by xmax⁡x_{\max}xmax​ in ℓ2\ell_2ℓ2​) and covariate diversity with constant λ0\lambda_0λ0​. Let C1=λ0/(40xmax⁡2)C_1 = \lambda_0/(40x_{\max}^2)C1​=λ0​/(40xmax2​). Then for each arm iii and each time t≥1t \ge 1t≥1, the sample covariance matrix Σ^(Si,t)=∑s∈Si,tXsXs⊤\hat\Sigma(\mathcal S_{i,t}) = \sum_{s \in \mathcal S_{i,t}} X_s X_s^\topΣ^(Si,t​)=∑s∈Si,t​​Xs​Xs⊤​ of that arm satisfies

P[λmin⁡(Σ^(Si,t))≥λ0t4]≥1−exp⁡(log⁡d−C1t).\mathbb P\Big[\lambda_{\min}\big(\hat\Sigma(\mathcal S_{i,t})\big) \ge \frac{\lambda_0 t}{4}\Big] \ge 1 - \exp(\log d - C_1 t).P[λmin​(Σ^(Si,t​))≥4λ0​t​]≥1−exp(logd−C1​t).

The greedy policy never explores deliberately, yet under covariate diversity each arm's sample covariance grows linearly in time with high probability. This is the step where Assumption 3 enters the regret analysis.

Formalization Note The margin condition is not assumed. Ties between the two estimates (in particular every early context, when both estimates are 000) are broken by an independent fair coin; with a deterministic tie rule the lemma would be false.

Preamble
import Mathlib
import Definitions.Def_MostlyExplorationFree_GreedyBandit_Model

open Matrix MeasureTheory ProbabilityTheory
Formal statement
namespace MostlyExplorationFree.GreedyBandit

theorem lemma_4 {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω) {d : ℕ} (hd : 1 ≤ d)
    (μ : Measure (Fin d → ℝ)) (X : ℕ → Ω → Fin d → ℝ) (ε : Fin 2 → ℕ → Ω → ℝ)
    (W : ℕ → Ω → Bool) (σ : ℝ) (β : Fin 2 → Fin d → ℝ) (xmax bmax lam0 : ℝ)
    (hmodel : IsGreedyModel P μ X ε W σ) (hA1 : ParameterSet μ β xmax bmax)
    (hA3 : CovariateDiversity μ lam0) (i : Fin 2) (t : ℕ) (ht : 1 ≤ t) :
    1 - Real.exp (Real.log d - C1 lam0 xmax * t)
      ≤ (P {ω | lam0 * t / 4 ≤ lambdaMin (gram β X ε W i t ω)}).toReal := by sorry

end MostlyExplorationFree.GreedyBandit
Source
Bastani, Bayati & Khosravi, arXiv:1704.09011v8, p. 14, Lemma 4
Human review
  • Endorsed by Shuze Chen · Oct 22, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 22, 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