Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 5 — Algorithm 2 converges linearly: E∥xk−x∗∥P≤N(C~+D~)q~k\mathbb E\|x_k - x^*\|_P \le \sqrt N(\tilde C + \tilde D)\tilde q^kE∥xk​−x∗∥P​≤N​(C~+D~)q~​k

Proved
LeiBR.Rand.lemma_5

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

linear-convergencep2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1randomized-algorithmsstochastic-nash-game

Let Assumptions 1 and 2 hold, μ>0\mu > 0μ>0, N≥1N \ge 1N≥1, and let x∗x^*x∗ be a Nash equilibrium. Let {xk}\{x_k\}{xk​} be generated by Algorithm 2 under Assumption 3, from a starting point with ∥xi,0−xi∗∥≤C\|x_{i,0} - x_i^*\| \le C∥xi,0​−xi∗​∥≤C for all iii. The inexactness is αi,k=ηβi,k+1\alpha_{i,k} = \eta^{\beta_{i,k}+1}αi,k​=ηβi,k​+1 for some η∈(0,1)\eta \in (0,1)η∈(0,1), where βi,k\beta_{i,k}βi,k​ is the number of updates of player iii before iteration kkk. Let c~=max⁡{a~,η~}\tilde c = \max\{\tilde a, \tilde\eta\}c~=max{a~,η~​}. Then for every q~∈(c~,1)\tilde q \in (\tilde c, 1)q~​∈(c~,1),

E[∥xk−x∗∥P]≤N (C~+D~) q~k∀k≥0,\mathbb E\big[\|x_k - x^*\|_P\big] \le \sqrt N\,(\tilde C + \tilde D)\,\tilde q^k \qquad \forall k \ge 0,E[∥xk​−x∗∥P​]≤N​(C~+D~)q~​k∀k≥0,

with ∥⋅∥P\|\cdot\|_P∥⋅∥P​ from (A.2), D=1/ln⁡((q~/c~)e)D = 1/\ln((\tilde q/\tilde c)^e)D=1/ln((q~​/c~)e), C~=C(∑i=1NN−1pi−1)1/2\tilde C = C\big(\sum_{i=1}^N N^{-1}p_i^{-1}\big)^{1/2}C~=C(∑i=1N​N−1pi−1​)1/2 and D~=Dηη~−1\tilde D = D\eta\tilde\eta^{-1}D~=Dηη~​−1.

This is the geometric rate of the randomized scheme. It reduces to Proposition 4 when every pi=1p_i = 1pi​=1.

Formalization Note The starting point is deterministic, and the paper's E∥xi,0−xi∗∥≤C\mathbb E\|x_{i,0} - x_i^*\| \le CE∥xi,0​−xi∗​∥≤C is read as ∥xi,0−xi∗∥≤C\|x_{i,0} - x_i^*\| \le C∥xi,0​−xi∗​∥≤C. The proof's step ∥x0−x∗∥P≤C(∑ipi−1)1/2\|x_0 - x^*\|_P \le C(\sum_i p_i^{-1})^{1/2}∥x0​−x∗∥P​≤C(∑i​pi−1​)1/2 needs this. The run is any run of the abstract scheme (IsAlg2Run) with αi,k=ηβi,k+1\alpha_{i,k} = \eta^{\beta_{i,k}+1}αi,k​=ηβi,k​+1.

Preamble
import Mathlib
import Definitions.Def_LeiBR_Rand_Game
import Definitions.Def_LeiBR_Rand_ProxBR
import Definitions.Def_LeiBR_Rand_Assumption1
import Definitions.Def_LeiBR_Rand_SA
import Definitions.Def_LeiBR_Rand_Algorithm2
import Definitions.Def_LeiBR_Rand_Constants

open MeasureTheory ProbabilityTheory
Formal statement
namespace LeiBR.Rand

/-- Lemma 5 (geometric convergence), p. 15. Let `x_k` be generated by Algorithm 2 with
`α_{i,k} = η^{β_{i,k}+1}`, `η ∈ (0,1)`, and `‖x_{i,0} − x*_i‖ ≤ C`, under Assumptions 1–3. Then for
every `q̃ ∈ (c̃, 1)`, `c̃ = max{ã, η̃}`,
`E‖x_k − x*‖_P ≤ √N (C̃ + D̃) q̃^k` for all `k ≥ 0`. -/
theorem lemma_5 {N : ℕ} {n : Fin N → ℕ} {d : ℕ} (G : Game N n)
    (μξ : Measure (EuclideanSpace ℝ (Fin d)))
    (ψ : Fin N → LeiBR.Sync.Profile n → EuclideanSpace ℝ (Fin d) → ℝ)
    (gψ : ∀ i, LeiBR.Sync.Profile n → EuclideanSpace ℝ (Fin d) → LeiBR.Sync.Strat n i) (M : Fin N → ℝ)
    (hA1 : Assumption1 G μξ ψ gψ M) (mu : ℝ) (hmu : 0 < mu)
    (xhat : LeiBR.Sync.Profile n → LeiBR.Sync.Profile n) (hxhat : IsProxBR G mu xhat)
    (hA2 : Assumption2 G mu) (xstar : LeiBR.Sync.Profile n) (hNE : G.IsNE xstar) (hN : 0 < N)
    {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω) [IsProbabilityMeasure P]
    (F : Filtration ℕ (inferInstance : MeasurableSpace Ω)) (p : Fin N → ℝ)
    (χ : Fin N → ℕ → Ω → ℕ) (w : ∀ i, ℕ → Ω → LeiBR.Sync.Strat n i) (x0 : LeiBR.Sync.Profile n)
    (x : ℕ → Ω → LeiBR.Sync.Profile n) (η : ℝ) (hη0 : 0 < η) (hη1 : η < 1)
    (C : ℝ) (hC : ∀ i, ‖x0 i - xstar i‖ ≤ C)
    (hrun : IsAlg2Run G xhat P F p χ w (fun i k ω => η ^ (beta χ i k ω + 1)) x0 x)
    (q : ℝ) (hq : ctil p (contrFactor G mu) η < q) (hq1 : q < 1) (k : ℕ) :
    ∫ ω, wnorm p (x k ω - xstar) ∂P ≤
      Real.sqrt N * (Ctil p C + Dtil p (contrFactor G mu) η q) * q ^ k := by sorry

end LeiBR.Rand
Source
Lei, Shanbhag, Pang & Sen, On Synchronous, Asynchronous, and Randomized Best-Response Schemes for Stochastic Nash Games, arXiv:1704.04578v2, p. 15, Lemma 5 (proof: App. B, pp. 32–33)
Human review
  • Endorsed by Shuze Chen · Oct 8, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 8, 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