Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Best-arm complexity optimization bridge

Proved
BanditAlgorithm.baiComplexity_mul_le_total_of_information_constraints_of_pos

by Harry_Xu · Jul 30, 2026 · Mathlib c5ea003 (Lean v4.30.0)

banditsbest-arm-identificationinformation-theorylower-boundsoptimization

Fix a bandit environment ν\nuν with k≥1k\ge1k≥1 arms in a class E\mathcal EE. Let ci∈[0,∞]c_i\in[0,\infty]ci​∈[0,∞] be nonnegative sampling weights and let L∈[0,∞]L\in[0,\infty]L∈[0,∞]. Suppose every alternative environment ν′∈Ealt(ν)\nu'\in\mathcal E_{\mathrm{alt}}(\nu)ν′∈Ealt​(ν) satisfies the information constraint

L≤∑i=1kciD(νi∥νi′).L\le \sum_{i=1}^k c_i D(\nu_i\Vert\nu_i').L≤i=1∑k​ci​D(νi​∥νi′​).

Then the characteristic best-arm-identification time obeys

c∗(ν) L≤∑i=1kci.c^*(\nu)\,L\le \sum_{i=1}^k c_i.c∗(ν)L≤i=1∑k​ci​.

This is the optimization step that converts per-alternative change-of-measure inequalities into the closed-form sample-complexity lower bound.

Formalization Note All quantities are extended nonnegative reals, including zero and infinite boundary cases.

Preamble
import Definitions.Def_BanditTrajectory

open MeasureTheory ProbabilityTheory InformationTheory ENNReal
Formal statement
theorem BanditAlgorithm.baiComplexity_mul_le_total_of_information_constraints_of_pos
    {k : ℕ} (hk : 0 < k) (𝓔 : Set (StochasticBandit k)) (ν : StochasticBandit k)
    (c : Fin k → ℝ≥0∞) (L : ℝ≥0∞)
    (hinfo : ∀ ν' ∈ baiAlternatives 𝓔 ν,
      L ≤ ∑ i, c i * klDiv (ν.P i) (ν'.P i)) :
    baiComplexity ν 𝓔 * L ≤ ∑ i, c i := by
  sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (CUP 2020), proof of Theorem 33.5, printed p. 407, Eq. (33.7).

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