Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Hard-game information–regret tradeoff optimization

Proved
BanditAlgorithm.partial_monitoring_hard_tradeoff_analytic

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

banditsinequalitiespartial-monitoring

Let ε,δ>0\varepsilon,\delta>0ε,δ>0 and C≥0C\ge0C≥0. Then there is a constant c>0c>0c>0, depending only on these three parameters, such that for every integer n≥1n\ge1n≥1 and every x≥0x\ge0x≥0,

εx2+nΔn8exp⁡(−CΔn2x)≥c n2/3,Δn=δn−1/3.\frac{\varepsilon x}{2}+\frac{n\Delta_n}{8}\exp(-C\Delta_n^2x)\ge c\,n^{2/3}, \qquad \Delta_n=\delta n^{-1/3}.2εx​+8nΔn​​exp(−CΔn2​x)≥cn2/3,Δn​=δn−1/3.

This is the elementary optimization that completes the hard partial-monitoring lower bound after the information/regret tradeoff has been established: either the exploration count xxx is already of order n2/3n^{2/3}n2/3, or the testing term remains a constant fraction of nΔnn\Delta_nnΔn​.

Preamble
import Mathlib.Analysis.SpecialFunctions.Pow.Real
import Mathlib.Analysis.SpecialFunctions.ExpDeriv
Formal statement
theorem BanditAlgorithm.partial_monitoring_hard_tradeoff_analytic
    (ε C δ : ℝ) (hε : 0 < ε) (hC : 0 ≤ C) (hδ : 0 < δ) :
    ∃ c : ℝ, 0 < c ∧ ∀ (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) ≥
        c * (n : ℝ) ^ ((2 : ℝ) / 3) := by sorry
Source
Lattimore and Szepesvári, Bandit Algorithms, Chapter 37, Theorem 37.12 proof, printed p. 491, final display and Exercise 37.7.

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