Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Geometric alternatives for a hard partial-monitoring edge

Proved
BanditAlgorithm.partial_monitoring_hard_geometric_alternatives

by Harry_Xu · Aug 5, 2026 · Mathlib 0df444a (Lean v4.33.1)

banditspartial-monitoring

Let GGG be globally observable but not locally observable. There exist neighbouring actions a,ba,ba,b, a base distribution uuu, a zero-sum normalized direction qqq, and constants ε,δ>0\varepsilon,\delta>0ε,δ>0 such that the alternatives u±Δqu\pm\Delta qu±Δq have the cell, loss-gap, feedback-indistinguishability, and Eq. (37.10) properties for every 0<Δ≤δ0<\Delta\le\delta0<Δ≤δ.

⟨ℓc−ℓa,u−Δq⟩+⟨ℓc−ℓb,u+Δq⟩=Δ.\langle\ell_c-\ell_a,u-\Delta q\rangle+\langle\ell_c-\ell_b,u+\Delta q\rangle=\Delta.⟨ℓc​−ℓa​,u−Δq⟩+⟨ℓc​−ℓb​,u+Δq⟩=Δ.

This packages the geometric half of the hard partial-monitoring lower bound.

Preamble
import Definitions.Def_PartialMonitoringGame
Formal statement
theorem BanditAlgorithm.partial_monitoring_hard_geometric_alternatives
    {k d : ℕ} {𝕊 : Type*} [Fintype 𝕊] [DecidableEq 𝕊]
    (G : BanditAlgorithm.PartialMonitoringGame k d 𝕊)
    (hglob : BanditAlgorithm.GloballyObservable G)
    (hloc : ¬ BanditAlgorithm.LocallyObservable G) :
    ∃ a b : Fin k, ∃ u q : Fin d → ℝ, ∃ ε δ : ℝ,
      BanditAlgorithm.NeighbouringActions G a b ∧ 0 < ε ∧ 0 < δ ∧
      (∑ i, q i) = 0 ∧
      (∑ i, (G.L a i - G.L b i) * q i) = 1 ∧
      (∀ c : Fin k, c ∈ BanditAlgorithm.pmNeighbourhood G a b → ∀ σ : 𝕊,
        ∑ i ∈ Finset.univ.filter (fun i ↦ G.Φ c i = σ), q i = 0) ∧
      ∀ Δ : ℝ, 0 < Δ → Δ ≤ δ →
        let ua := fun i ↦ u i - Δ * q i
        let ub := fun i ↦ u i + Δ * q i
        ua ∈ BanditAlgorithm.pmCell G a ∧ ub ∈ BanditAlgorithm.pmCell G b ∧
        (∀ c : Fin k, c ∉ BanditAlgorithm.pmNeighbourhood G a b →
          ε / 2 ≤ ∑ i, (G.L c i - G.L a i) * ua i ∧
          ε / 2 ≤ ∑ i, (G.L c i - G.L b i) * ub i) ∧
        (∀ c : Fin k, c ∈ BanditAlgorithm.pmNeighbourhood G a b →
          (∑ i, (G.L c i - G.L a i) * ua i) +
          (∑ i, (G.L c i - G.L b i) * ub i) = Δ) :=
  by sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (Cambridge UP, 2020), Theorem 37.12, Steps 1 and 3, printed pp. 488–491, Eqs. (37.5)–(37.7) and (37.10); Lemma 37.8(a), printed pp. 484–485.

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