Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

One-phase Sequential Halving elimination bound

Disproved
BanditAlgorithm.sequential_halving_phase_elimination_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⌉, and fix a phase ℓ<L\ell<Lℓ<L. Consider a kkk-armed 111-subgaussian bandit with means indexed in nonincreasing order, budget n≥kLn\ge kLn≥kL, and complexity bound i/Δi2≤H2i/\Delta_i^2\le H_2i/Δi2​≤H2​ for each suboptimal arm.

Under any policy, the probability that a complete Sequential Halving run eliminates the optimal arm during phase ℓ\ellℓ satisfies

P(1∈Aℓ, 1∉Aℓ+1)≤3exp⁡ ⁣(−n16H2L).\mathbb P(1\in A_\ell,\ 1\notin A_{\ell+1}) \le 3\exp\!\left(-\frac{n}{16H_2L}\right).P(1∈Aℓ​, 1∈/Aℓ+1​)≤3exp(−16H2​Ln​).

This is the uniform one-phase concentration estimate whose union over the LLL phases yields the complete Sequential Halving failure bound.

Formalization Note The event is expressed by IsSeqHalvingEliminationAt, which includes the active-set and fresh-phase-sampling invariants.

Preamble
import Definitions.Def_SequentialHalvingPhaseElimination

open MeasureTheory
Formal statement
theorem BanditAlgorithm.sequential_halving_phase_elimination_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) (ℓ : ℕ) (hℓ : ℓ < Nat.clog 2 k) :
    (banditMeasure ν π n).real {h | IsSeqHalvingEliminationAt k n h ℓ} ≤
      3 * Real.exp (-(n / (16 * H₂ * (Nat.clog 2 k : ℝ)))) := by
  sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (CUP 2020), Exercise 33.8(b)–(e), printed pp. 419–420.

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