Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Exp4 regret bound at a general learning rate

Proved
BanditAlgorithm.exp4_regret_general_eta_bound

by Harry_Xu · Jul 28, 2026 · Mathlib 0df444a (Lean v4.33.1)

adversarialbanditsconcentrationcontextual

Let k≥1k\ge 1k≥1, M≥2M\ge 2M≥2, and n≥1n\ge 1n≥1. Let the learning rate satisfy η>0\eta>0η>0. In each round ttt, the adversarial reward vector has coordinates xt,a∈[0,1]x_{t,a}\in[0,1]xt,a​∈[0,1], and every expert advice row Et(m)E_t^{(m)}Et(m)​ is a probability distribution over the kkk arms. If the learner follows Exp4 with learning rate η\etaη and exploration parameter γ=0\gamma=0γ=0, then its expected regret against the best of the MMM oblivious experts satisfies

Rn≤log⁡Mη+ηnk2.R_n\le \frac{\log M}{\eta}+\frac{\eta nk}{2}.Rn​≤ηlogM​+2ηnk​.

This is the reusable, pre-optimization form of the Exp4 regret theorem. Choosing the learning rate as a function of nnn, kkk, and MMM yields the usual square-root regret bound.

Formalization Note The expected regret is exp4Regret; the predicate IsExp4Policy fixes the history-dependent policy to Algorithm 11.

Preamble
import Definitions.Def_ContextualAdversarialBandit
import Definitions.Def_exp4Policy

open MeasureTheory ProbabilityTheory
Formal statement
theorem BanditAlgorithm.exp4_regret_general_eta_bound
    {k M : ℕ} (hk : 0 < k) (hM : 1 < M) (n : ℕ) (hn : 0 < n)
    (η : ℝ) (hη : 0 < η)
    (x : ℕ → Fin k → ℝ) (hx : ∀ t : ℕ, ∀ a : Fin k, x t a ∈ Set.Icc (0 : ℝ) 1)
    (E : ℕ → Fin M → Fin k → ℝ)
    (hE0 : ∀ t : ℕ, ∀ m : Fin M, ∀ a : Fin k, 0 ≤ E t m a)
    (hE1 : ∀ t : ℕ, ∀ m : Fin M, ∑ a, E t m a = 1)
    (π : BanditPolicy k)
    (hπ : IsExp4Policy η 0 E π) :
    exp4Regret n x E π ≤
      Real.log M / η + η * ((n : ℝ) * k) / 2 := by
  sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (2020), Theorem 18.1 proof, printed p. 230, especially Eqs. (18.11) and (18.12), with the substitution immediately before Eq. (18.7).

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