Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

One-step information-ratio bound with arm-dependent reference laws

Proved
BanditAlgorithm.thompson_sampling_one_step_information_ratio_varying_reference

by Harry_Xu · Aug 2, 2026 · Mathlib c5ea003 (Lean v4.30.0)

banditsinformation-theoryprobability

Let pap_apa​ be real weights. For every arm a∈[k]a\in[k]a∈[k], let PaP_aPa​ and MaM_aMa​ be probability measures on the same measurable space, and let rar_ara​ be a measurable function taking values in [0,1][0,1][0,1]. If every D(Pa∥Ma)D(P_a\|M_a)D(Pa​∥Ma​) is finite, then

(∑a=1kpa(EPara−EMara))2≤k2∑a=1kpa2D(Pa∥Ma).\left(\sum_{a=1}^k p_a\bigl(\mathbb E_{P_a}r_a-\mathbb E_{M_a}r_a\bigr)\right)^2 \le \frac{k}{2}\sum_{a=1}^k p_a^2D(P_a\|M_a).(a=1∑k​pa​(EPa​​ra​−EMa​​ra​))2≤2k​a=1∑k​pa2​D(Pa​∥Ma​).

This is the analytic Pinsker–Cauchy–Schwarz step in the one-round Thompson-sampling information-ratio argument, allowing the reference distribution to depend on the arm.

Preamble
import Mathlib.InformationTheory.KullbackLeibler.Basic

open MeasureTheory InformationTheory
open scoped ENNReal BigOperators
Formal statement
namespace BanditAlgorithm

theorem thompson_sampling_one_step_information_ratio_varying_reference
    {k : ℕ} {Omega : Type} {mOmega : MeasurableSpace Omega}
    (p : Fin k → ℝ) (P M : Fin k → Measure Omega)
    [∀ a, IsProbabilityMeasure (P a)] [∀ a, IsProbabilityMeasure (M a)]
    (reward : Fin k → Omega → ℝ)
    (hreward : ∀ a, Measurable (reward a))
    (hreward0 : ∀ a x, 0 ≤ reward a x)
    (hreward1 : ∀ a x, reward a x ≤ 1)
    (hfinite : ∀ a, klDiv (P a) (M a) ≠ ∞) :
    (∑ a, p a * ((∫ x, reward a x ∂(P a)) - ∫ x, reward a x ∂(M a))) ^ 2 ≤
      ((k : ℝ) / 2) * ∑ a, p a ^ 2 * (klDiv (P a) (M a)).toReal := by
  sorry

end BanditAlgorithm
Source
Lattimore and Szepesvári, Bandit Algorithms (2020), Lemma 36.7, printed p. 470 (free PDF p. 479), https://tor-lattimore.com/downloads/book/book.pdf; Pinsker and Cauchy–Schwarz steps.

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