Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Sequential Halving bad-final probability with LLL phases

Proved
BanditAlgorithm.sequential_halving_bad_final_probability_bound_clog

by Harry_Xu · Aug 2, 2026 · Mathlib c5ea003 (Lean v4.30.0)

banditsbest-arm-identificationconcentrationsequential-halving

Let L=⌈log⁡2k⌉L=\lceil\log_2 k\rceilL=⌈log2​k⌉. For a sorted 111-subgaussian bandit, budget n≥kLn\ge kLn≥kL, and complexity bound i/Δi2≤H2i/\Delta_i^2\le H_2i/Δi2​≤H2​, consider the event that a complete Sequential Halving active-set chain starts with an optimal arm but its final active set contains only suboptimal arms. Under any policy,

P(no optimal arm survives)≤3Lexp⁡ ⁣(−n16H2L).\mathbb P(\text{no optimal arm survives}) \le 3L\exp\!\left(-\frac{n}{16H_2L}\right).P(no optimal arm survives)≤3Lexp(−16H2​Ln​).

This is the recommendation-independent concentration core of the general-kkk Sequential Halving guarantee. It remains correct when several arms are optimal.

Preamble
import Definitions.Def_SequentialHalvingBadFinal

open MeasureTheory
Formal statement
theorem BanditAlgorithm.sequential_halving_bad_final_probability_bound_clog {k n : ℕ}
    (ν : StochasticBandit k) (hν : IsSubgaussianBandit 1 ν)
    (hsorted : ∀ i j : Fin k, i ≤ j → banditArmMean ν j ≤ banditArmMean ν i)
    (hn : k * Nat.clog 2 k ≤ n) (H₂ : ℝ)
    (hH₂ : ∀ i : Fin k, 0 < banditGap ν i →
      ((i : ℕ) + 1 : ℝ) / banditGap ν i ^ 2 ≤ H₂)
    (π : BanditPolicy k) :
    (banditMeasure ν π n).real {h | IsSeqHalvingBadFinalRun k n ν h} ≤
      3 * (Nat.clog 2 k : ℝ) *
        Real.exp (-(n / (16 * H₂ * (Nat.clog 2 k : ℝ)))) := by
  sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (CUP 2020), Exercise 33.8(c)–(f), printed pp. 419–420; direct general-k phase-count form.

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