Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 4 — geometric rate uk≤N(C+D)qku_k\le\sqrt N(C+D)q^kuk​≤N​(C+D)qk of Algorithm 1 with αi,k=ηk+1\alpha_{i,k}=\eta^{k+1}αi,k​=ηk+1

Proved
LeiBR.Sync.prop_4

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

best-responseconvergence-ratep2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1stochastic-nash-game

Assume Assumptions 1 and 2, μ>0\mu>0μ>0, and let x∗x^*x∗ be a Nash equilibrium. Run Algorithm 1 (abstract form) from a deterministic x0∈Xx_0\in Xx0​∈X with ∥xi,0−xi∗∥≤C\|x_{i,0}-x_i^*\|\le C∥xi,0​−xi∗​∥≤C for all iii, and with αi,k=ηk+1\alpha_{i,k}=\eta^{k+1}αi,k​=ηk+1 for some η∈(0,1)\eta\in(0,1)η∈(0,1). Let a=∥Γ∥a=\|\Gamma\|a=∥Γ∥, c=max⁡{a,η}c=\max\{a,\eta\}c=max{a,η}, q∈(c,1)q\in(c,1)q∈(c,1) and

D=1ln⁡((q/c)e)=1eln⁡(q/c).D=\frac{1}{\ln\big((q/c)^e\big)}=\frac1{e\ln(q/c)} .D=ln((q/c)e)1​=eln(q/c)1​.

Then, with uku_kuk​ the mean Euclidean norm of the vector of block errors (18),

uk≤N (C+D) qk∀k≥0.u_k\le\sqrt N\,(C+D)\,q^k\qquad\forall k\ge0 .uk​≤N​(C+D)qk∀k≥0.

The inexact scheme thus keeps a linear rate, arbitrarily close to max⁡{a,η}\max\{a,\eta\}max{a,η}, and the number of players enters only through the constant.

Formalization Note The initial point is deterministic, as in Algorithm 1 ("Let yi,0=xi,0∈Xiy_{i,0}=x_{i,0}\in X_iyi,0​=xi,0​∈Xi​"), so E∥xi,0−xi∗∥≤C\mathbb E\|x_{i,0}-x_i^*\|\le CE∥xi,0​−xi∗​∥≤C reads ∥xi,0−xi∗∥≤C\|x_{i,0}-x_i^*\|\le C∥xi,0​−xi∗​∥≤C; the proof's step u0≤NCu_0\le\sqrt N Cu0​≤N​C needs this.

Preamble
import Mathlib
import Definitions.Def_LeiBR_Sync_NashGame
import Definitions.Def_LeiBR_Sync_StochGame
import Definitions.Def_LeiBR_Sync_Algorithm1

open MeasureTheory
Formal statement
namespace LeiBR.Sync

/-- Proposition 4, p. 9 (geometric rate): for Algorithm 1 with `α_{i,k} = η^{k+1}`,
`η ∈ (0, 1)`, and a deterministic initial point with `‖x_{i,0} - x*_i‖ ≤ C`, put `a = ‖Γ‖`,
`c = max{a, η}`, `q ∈ (c, 1)` and `D = 1/ln((q/c)^e) = 1/(e ln(q/c))`. Then
`u_k = E‖(‖x_{i,k} - x*_i‖)_i‖ ≤ √N (C + D) q^k` for all `k ≥ 0`. -/
theorem prop_4
    {N : ℕ} {n : Fin N → ℕ} {Ω : Type*} [mΩ : MeasurableSpace Ω] (P : Measure Ω)
    [IsProbabilityMeasure P] {d : ℕ} (ξ : Ω → EuclideanSpace ℝ (Fin d))
    (X : ∀ i : Fin N, Set (Strat n i)) (ψ : Fin N → Profile n → EuclideanSpace ℝ (Fin d) → ℝ)
    (gψ : ∀ i : Fin N, Profile n → EuclideanSpace ℝ (Fin d) → Strat n i) (M : Fin N → ℝ)
    (hA1 : Assumption1 P ξ X ψ gψ M) (μ : ℝ) (hμ : 0 < μ)
    (hA2 : Assumption2 X (payoff P ξ ψ) μ)
    (xhat : Profile n → Profile n) (hxhat : IsProxBR X (payoff P ξ ψ) μ xhat)
    (xs : Profile n) (hxs : IsNashEq X (payoff P ξ ψ) xs)
    (F : Filtration ℕ mΩ) (η : ℝ) (hη0 : 0 < η) (hη1 : η < 1)
    (x0 : Profile n) (x : ℕ → Ω → Profile n)
    (hx : IsAlg1 P F X xhat (fun _ k => η ^ (k + 1)) x0 x)
    (C : ℝ) (hC : ∀ i : Fin N, ‖x0 i - xs i‖ ≤ C)
    (q : ℝ) (hcq : max (specNorm (Gamma X (payoff P ξ ψ) μ)) η < q) (hq1 : q < 1)
    (D : ℝ) (hD : D = 1 / (Real.exp 1 *
      Real.log (q / max (specNorm (Gamma X (payoff P ξ ψ) μ)) η))) :
    ∀ k : ℕ, ∫ ω, blockDist (x k ω) xs ∂P ≤ Real.sqrt N * (C + D) * q ^ k := by sorry

end LeiBR.Sync
Source
Lei, Shanbhag, Pang & Sen, On Synchronous, Asynchronous, and Randomized Best-Response Schemes for Stochastic Nash Games, arXiv:1704.04578v2, p. 9, Proposition 4, (18)–(19)
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