Prove2Me
Navigate
DiscoverCollectionsFormalpediaBlogsUsersMomentumMy Missions+
Prove2Me
⌕
Log in
← Formalpedia

Lemma B.2, p. 21 — for a reversible policy chain, ρ(B_π) = (1 − √(1/κ))/(1 + √(1/κ)) (printed (1 − √κ)/(1 + √κ))

Proved
AccelVI.MVC.lemma_B_2

by mikedeng1 · Oct 15, 2026 · Mathlib 0df444a (Lean v4.33.1)

momentump2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1reversible-markov-chainspectral-radius

Let (S,A,P,r,λ)(S, A, P, r, \lambda)(S,A,P,r,λ) be a valid finite MDP and π\piπ a policy whose transition matrix LπL_\piLπ​ defines an irreducible, reversible Markov chain, and let BπB_\piBπ​ be the matrix of App. B built with the constant step sizes (4.2). With κ=(1+λ)/(1−λ)\kappa = (1+\lambda)/(1-\lambda)κ=(1+λ)/(1−λ), the spectral radius of BπB_\piBπ​ is

ρ(Bπ)=1−1/κ1+1/κ.\rho(B_\pi) = \frac{1 - \sqrt{1/\kappa}}{1 + \sqrt{1/\kappa}} .ρ(Bπ​)=1+1/κ​1−1/κ​​.

Together with Lemma B.1 this gives the linear convergence rate of Momentum Value Computation in Theorem 5.5.

Formalization Note. The lemma prints ρ(Bπ)=(1−κ)/(1+κ)\rho(B_\pi) = (1-\sqrt{\kappa})/(1+\sqrt{\kappa})ρ(Bπ​)=(1−κ​)/(1+κ​), which is negative since κ>1\kappa > 1κ>1 and so cannot be a spectral radius; the proof's final display computes λ/(1+1−λ2)=(1−1/κ)/(1+1/κ)\lambda/(1+\sqrt{1-\lambda^2}) = (1-\sqrt{1/\kappa})/(1+\sqrt{1/\kappa})λ/(1+1−λ2​)=(1−1/κ​)/(1+1/κ​), the rate of Theorem 5.5, which is the value stated. The spectral radius is that of the complexified matrix over C\mathbb{C}C, an extended nonnegative real compared with the (positive) rate.

Preamble
import Mathlib
import Definitions.Def_mm_basic
import Definitions.Def_AccelVI_MVC_Setting
Formal statement
namespace AccelVI.MVC

variable {S A : Type*} [Fintype S] [DecidableEq S] [Fintype A]

/-- Lemma B.2, p. 21 (with the rate (1 − √(1/κ))/(1 + √(1/κ)) of its proof for the printed
(1 − √κ)/(1 + √κ)): if π defines an irreducible, reversible Markov chain, then for step sizes (4.2)
ρ(B_π) = (1 − √(1/κ))/(1 + √(1/κ)). -/
theorem lemma_B_2 (M : MDP S A) (hM : M.Valid) (pol : S → A → ℝ) (hpol : IsPolicy pol)
    (hrev : AccelVI.AVC.IsReversible (LPol M pol)) :
    spectralRadius ℂ ((Bpol M pol).map (algebraMap ℝ ℂ)) = ENNReal.ofReal (rateMVC M.lam) := by sorry

end AccelVI.MVC
Source
Goyal & Grand-Clément, A First-Order Approach to Accelerated Value Iteration, arXiv:1905.09963v7, p. 21, Lemma B.2 (constant corrected per its proof, p. 22)
Human review
  • Endorsed by Shuze Chen · Oct 15, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 15, 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 paper
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me