Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Finite-action Cauchy–Schwarz information-ratio step

Proved
BanditAlgorithm.finite_information_ratio_cauchy_schwarz

by Harry_Xu · Aug 1, 2026 · Mathlib c5ea003 (Lean v4.30.0)

banditscauchy-schwarzinformation-theory

For real vectors ppp, ggg, and III indexed by kkk actions, suppose each coordinate satisfies 2ga2≤Ia2g_a^2\le I_a2ga2​≤Ia​. Then

(∑apaga)2≤k2∑apa2Ia.\left(\sum_a p_a g_a\right)^2 \le \frac{k}{2}\sum_a p_a^2 I_a.(a∑​pa​ga​)2≤2k​a∑​pa2​Ia​.

This is the finite-dimensional Cauchy–Schwarz step used in the Thompson-sampling information-ratio bound.

Preamble
import Mathlib.Algebra.Order.Chebyshev
import Mathlib.Data.Real.Basic

open scoped BigOperators
Formal statement
theorem BanditAlgorithm.finite_information_ratio_cauchy_schwarz {k : ℕ}
    (p gap info : Fin k → ℝ)
    (hpoint : ∀ a, 2 * gap a ^ 2 ≤ info a) :
    (∑ a, p a * gap a) ^ 2 ≤
      ((k : ℝ) / 2) * ∑ a, p a ^ 2 * info a := by
  sorry
Source
Lattimore and Szepesvári, Bandit Algorithms (Cambridge UP, 2020), https://tor-lattimore.com/downloads/book/book.pdf, printed p. 470 (PDF p. 479), proof of Lemma 36.7, the Cauchy–Schwarz inequality immediately before the final Bayes-rule equality.

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