Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Hard-game geometric and information–regret tradeoff

Proved
BanditAlgorithm.partial_monitoring_hard_game_tradeoff

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

banditsinformation-theorypartial-monitoring

Let GGG be a finite globally observable but not locally observable partial-monitoring game. Then there are game-dependent constants ε,δ>0\varepsilon,\delta>0ε,δ>0 and C≥0C\ge0C≥0 such that for every horizon n≥1n\ge1n≥1 there is an expected off-neighbourhood play count x≥0x\ge0x≥0 satisfying

εx2+nΔn8exp⁡(−CΔn2x)≤2Rn∗(G),Δn=δn−1/3.\frac{\varepsilon x}{2}+\frac{n\Delta_n}{8}\exp(-C\Delta_n^2x)\le 2R_n^*(G), \qquad \Delta_n=\delta n^{-1/3}.2εx​+8nΔn​​exp(−CΔn2​x)≤2Rn∗​(G),Δn​=δn−1/3.

The first term is the regret paid for informative actions outside the critical neighbourhood; the second is the testing cost for distinguishing the two stochastic environments constructed around a non-locally-observable neighbouring pair. This is precisely the geometric and information-theoretic core of the hard-game lower bound.

Preamble
import Definitions.Def_PartialMonitoringGame
import Mathlib.Analysis.SpecialFunctions.Pow.Real

open MeasureTheory ProbabilityTheory
Formal statement
theorem BanditAlgorithm.partial_monitoring_hard_game_tradeoff {k d : ℕ} {𝕊 : Type*}
    [Fintype 𝕊] [MeasurableSpace 𝕊] (G : PartialMonitoringGame k d 𝕊)
    (hglob : GloballyObservable G) (hloc : ¬ LocallyObservable G) :
    ∃ ε C δ : ℝ, 0 < ε ∧ 0 ≤ C ∧ 0 < δ ∧
      ∀ (n : ℕ), 1 ≤ n → ∃ x : ℝ, 0 ≤ x ∧
        ε / 2 * x +
            (n : ℝ) * (δ * (n : ℝ) ^ (-(1 : ℝ) / 3)) / 8 *
              Real.exp (-C * (δ * (n : ℝ) ^ (-(1 : ℝ) / 3)) ^ 2 * x) ≤
          2 * pmMinimaxRegret G n := by sorry
Source
Lattimore and Szepesvári, Bandit Algorithms, Chapter 37, Theorem 37.12 proof, printed pp. 488–491: Step 1 and Eq. (37.5)–(37.7), Step 2 Eq. (37.8)–(37.9), Step 3 Eq. (37.10) and the Bretagnolle–Huber display.

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