Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 5 extension — feasibility and complementary slackness

Proved
PandoraBO.Private20261023.complementary_lagrangian_certificate

by QianJaneXie · Oct 23, 2026 · Mathlib 0df444a (Lean v4.33.1)

bayesian-optimizationexpected-budgetgittins-indexpandoras-box

For any real budget BBB and nonnegative multiplier λ\lambdaλ, suppose a policy π\piπ maximizes R(ρ)−λC(ρ)R(\rho)-\lambda C(\rho)R(ρ)−λC(ρ) over all measurable adaptive randomized policies. If

C(π)≤B,λ(B−C(π))=0,C(\pi)\le B,\qquad \lambda(B-C(\pi))=0,C(π)≤B,λ(B−C(π))=0,

then π\piπ is budget-optimal: every policy ρ\rhoρ with C(ρ)≤BC(\rho)\le BC(ρ)≤B satisfies R(ρ)≤R(π)R(\rho)\le R(\pi)R(ρ)≤R(π). Unlike exact-budget matching, this sufficient condition includes λ=0\lambda=0λ=0 and unused budget. This is an explicit extension of Lemma 5, not a verbatim source statement.

Preamble
import Definitions.Def_PandoraBO_Model

set_option autoImplicit false
Formal statement
namespace PandoraBO.Private20261023

theorem complementary_lagrangian_certificate {n : ℕ} (M : Instance n)
    (B multiplier : ℝ) (hnonneg : 0 ≤ multiplier) (π : Policy n)
    (hopt : optimal M multiplier π) (hfeasible : budgetFeasible M B π)
    (hcomp : complementarySlackness M B multiplier π) :
    budgetOptimal M B π := by sorry

end PandoraBO.Private20261023
Source
Qian Xie, Raul Astudillo, Peter I. Frazier, Ziv Scully, and Alexander Terenin. [Cost-aware Bayesian Optimization via the Pandora's Box Gittins Index](https://arxiv.org/abs/2406.20062). NeurIPS 2024. Appendix B.5: the Lagrangian budget-optimality argument with complementary slackness, including the zero-multiplier case. This milestone isolates a proof step.
Human review
  • Endorsed by Shuze Chen · Oct 24, 2026

    Confirmed by the moderator at approval.

  • Endorsed by QianJaneXie · Oct 24, 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