Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eq. (3.12) — high-probability regret of Exp3.P for general parameters

Proved
RegretBandits.Adversarial.exp3P_regret_general

by mikedeng1 · Oct 4, 2026 · Mathlib 0df444a (Lean v4.33.1)

adversarial-banditsbanditshigh-probabilityp2o-batch-pfp1bp2o-gran-per-chapterp2o-plan-bookp2o-v1

Let K≥2K \ge 2K≥2, n≥1n \ge 1n≥1, and consider any adaptive adversary with gains in [0,1][0,1][0,1]. Run Exp3.P with parameters β∈(0,1]\beta \in (0,1]β∈(0,1], η>0\eta > 0η>0 and γ\gammaγ satisfying

γ≤12,(1+β)Kη≤γ.\gamma \le \tfrac12, \qquad (1+\beta) K \eta \le \gamma .γ≤21​,(1+β)Kη≤γ.

Then for every δ∈(0,1)\delta \in (0,1)δ∈(0,1), with probability at least 1−δ1-\delta1−δ, the regret Rn=max⁡i∑t=1ngi,t−∑t=1ngIt,tR_n = \max_i \sum_{t=1}^n g_{i,t} - \sum_{t=1}^n g_{I_t,t}Rn​=maxi​∑t=1n​gi,t​−∑t=1n​gIt​,t​ satisfies

Rn≤βnK+γn+(1+β)ηKn+ln⁡(Kδ−1)β+ln⁡Kη.R_n \le \beta n K + \gamma n + (1+\beta)\eta K n + \frac{\ln(K\delta^{-1})}{\beta} + \frac{\ln K}{\eta}.Rn​≤βnK+γn+(1+β)ηKn+βln(Kδ−1)​+ηlnK​.

This is the general bound proved in the course of Theorem 3.2; the tuned bounds (3.10) and (3.11) follow by substituting the parameters.

Formalization Note The book's Exp3.P has β∈[0,1]\beta \in [0,1]β∈[0,1] and η>0\eta > 0η>0; strict β>0\beta > 0β>0 is needed because the bound divides by β\betaβ. The hypotheses force γ>0\gamma > 0γ>0.

Preamble
import Mathlib
import Definitions.Def_RegretBandits_Adversarial_Protocol
import Definitions.Def_RegretBandits_Adversarial_Exp3P

open MeasureTheory
Formal statement
namespace RegretBandits.Adversarial

/-- Eq. (3.12) (Bubeck–Cesa-Bianchi, arXiv:1204.5721v2, p. 30, proof of Theorem 3.2). If Exp3.P is
run with `0 < β ≤ 1`, `η > 0`, `γ ≤ 1/2` and `(1 + β) K η ≤ γ` against any adaptive adversary
with gains in `[0,1]`, then for every `δ ∈ (0,1)`, with probability at least `1 - δ`,
`R_n ≤ β n K + γ n + (1 + β) η K n + ln(K δ⁻¹) / β + ln K / η`. -/
theorem exp3P_regret_general {K : ℕ} (hK : 2 ≤ K) (n : ℕ) (hn : 1 ≤ n) (g : Adversary K)
    (β γ η δ : ℝ) (hβ0 : 0 < β) (hβ1 : β ≤ 1) (hη : 0 < η) (hγ : γ ≤ 1 / 2)
    (hβηγ : (1 + β) * K * η ≤ γ) (hδ0 : 0 < δ) (hδ1 : δ < 1)
    {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω) [IsProbabilityMeasure P]
    (I : ℕ → Ω → Fin K) (hI : IsRun P (exp3PProb β γ η g) I) :
    ENNReal.ofReal (1 - δ) ≤
      P {ω | regret g n I ω ≤
        β * n * K + γ * n + (1 + β) * η * K * n + Real.log (K * δ⁻¹) / β + Real.log K / η} := by sorry

end RegretBandits.Adversarial
Source
Bubeck, Cesa-Bianchi, Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, arXiv:1204.5721v2, p. 30, Eq. (3.12) (proof of Theorem 3.2)
Human review
  • Endorsed by Shuze Chen · Oct 4, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 4, 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