Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

A nonlocally observable edge admits an indistinguishable perturbation direction

Proved
BanditAlgorithm.partial_monitoring_nonlocal_edge_direction

by Harry_Xu · Aug 5, 2026 · Mathlib c5ea003 (Lean v4.30.0)

banditsinformation-theorylinear-algebrapartial-monitoring

Fix neighbouring actions a,ba,ba,b in a finite partial-monitoring game, and suppose their loss difference has no estimator supported on the neighbourhood NabN_{ab}Nab​. Then there is a direction q∈Rdq\in\mathbb R^dq∈Rd satisfying

∑iqi=0,⟨ℓa−ℓb,q⟩=1,\sum_i q_i=0,\qquad \langle \ell_a-\ell_b,q\rangle=1,i∑​qi​=0,⟨ℓa​−ℓb​,q⟩=1,

and, for every c∈Nabc\in N_{ab}c∈Nab​ and every feedback symbol σ\sigmaσ,

∑i: Φci=σqi=0.\sum_{i:\,\Phi_{ci}=\sigma}q_i=0.i:Φci​=σ∑​qi​=0.

Thus the perturbations u±Δqu\pm\Delta qu±Δq preserve total probability and induce identical feedback distributions for every action in NabN_{ab}Nab​, while separating the expected losses of aaa and bbb at unit rate.

Preamble
import Definitions.Def_PartialMonitoringGame
import Mathlib.Analysis.InnerProductSpace.PiL2
import Mathlib.Analysis.InnerProductSpace.Projection.FiniteDimensional
Formal statement
theorem BanditAlgorithm.partial_monitoring_nonlocal_edge_direction
    {k d : ℕ} {𝕊 : Type*} [Fintype 𝕊] [DecidableEq 𝕊]
    (G : PartialMonitoringGame k d 𝕊) (a b : Fin k)
    (hab : NeighbouringActions G a b)
    (hnlocal : ¬ ∃ f : Fin k × 𝕊 → ℝ, IsLocalLossEstimator G a b f) :
    ∃ q : Fin d → ℝ,
      (∑ i, q i) = 0 ∧
      (∑ i, (G.L a i - G.L b i) * q i) = 1 ∧
      ∀ c : Fin k, c ∈ pmNeighbourhood G a b → ∀ σ : 𝕊,
        (∑ i ∈ Finset.univ.filter (fun i ↦ G.Φ c i = σ), q i) = 0 := by sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (Cambridge UP, 2020), Theorem 37.12, Step 1, printed pp. 489–490, Eq. (37.6) and the construction immediately following it.

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