Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 7, p. 5 — OFTRL with Mᵗ = uᵗ⁻¹ satisfies RVU with α = R/η, β = η, γ = 1/(4η)

Proved
RegLearnGames.IndivRegret.proposition_7

by mikedeng1 · Oct 9, 2026 · Mathlib 0df444a (Lean v4.33.1)

no-regret-dynamicsoptimistic-ftrlp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1regretrvu

Let R\mathcal RR be a regularizer on Rd\mathbb R^dRd that is 1-strongly convex with respect to ∥⋅∥1\|\cdot\|_1∥⋅∥1​ on the simplex Δ\DeltaΔ, let η>0\eta>0η>0, and let RRR bound the range of R\mathcal RR on Δ\DeltaΔ: R(f)−R(g)≤R\mathcal R(f)-\mathcal R(g)\le RR(f)−R(g)≤R for all f,g∈Δf,g\in\Deltaf,g∈Δ. Let u0,u1,…u^0,u^1,\dotsu0,u1,… be any utility sequence in Rd\mathbb R^dRd and let w0,w1,…w^0,w^1,\dotsw0,w1,… be a run of optimistic FTRL with regularizer R\mathcal RR, step size η\etaη and one-step recency bias Mt=ut−1M^t=u^{t-1}Mt=ut−1. Then for every horizon TTT and every comparator w∗∈Δw^*\in\Deltaw∗∈Δ,

∑t=1T⟨w∗−wt,ut⟩≤Rη+η∑t=1T∥ut−ut−1∥∞2−14η∑t=1T∥wt−wt−1∥12.\sum_{t=1}^T\langle w^*-w^t,u^t\rangle\le\frac R\eta+\eta\sum_{t=1}^T\|u^t-u^{t-1}\|_\infty^2-\frac1{4\eta}\sum_{t=1}^T\|w^t-w^{t-1}\|_1^2 .t=1∑T​⟨w∗−wt,ut⟩≤ηR​+ηt=1∑T​∥ut−ut−1∥∞2​−4η1​t=1∑T​∥wt−wt−1∥12​.

This is the RVU property (Regret bounded by Variation in Utilities, Definition 3 of the paper) with constants α=R/η\alpha=R/\etaα=R/η, β=η\beta=\etaβ=η, γ=1/(4η)\gamma=1/(4\eta)γ=1/(4η). The negative movement term is what lets the regret of interacting players stay small.

Formalization Note "Satisfies the RVU property" is formalized as inequality (1) holding on every utility sequence, which is what the quantification over uuu gives; the side conditions α>0\alpha>0α>0, 0<β≤γ0<\beta\le\gamma0<β≤γ of Definition 3 are conditions on the constants and are not part of the conclusion. The paper's R=sup⁡ΔR−inf⁡ΔRR=\sup_\Delta\mathcal R-\inf_\Delta\mathcal RR=supΔ​R−infΔ​R is replaced by any upper bound on that range, which includes the exact range. The norm is ∥⋅∥1\|\cdot\|_1∥⋅∥1​ with dual ∥⋅∥∞\|\cdot\|_\infty∥⋅∥∞​. This statement coincides with the one of the companion mission I of this series.

Preamble
import Mathlib
import Definitions.Def_RegLearnGames_TotalRegret_Setting
Formal statement
namespace RegLearnGames.IndivRegret

theorem proposition_7 {d : ℕ} (𝓡 : (Fin d → ℝ) → ℝ) (η : ℝ) (hη : 0 < η)
    (h𝓡 : RegLearnGames.TotalRegret.IsOneStronglyConvexL1 𝓡) (R : ℝ)
    (hR : ∀ f ∈ stdSimplex ℝ (Fin d), ∀ g ∈ stdSimplex ℝ (Fin d), 𝓡 f - 𝓡 g ≤ R)
    (u w : ℕ → Fin d → ℝ) (hw : RegLearnGames.TotalRegret.IsOFTRL 𝓡 η (fun T => u (T - 1)) u w)
    (T : ℕ) (wstar : Fin d → ℝ) (hwstar : wstar ∈ stdSimplex ℝ (Fin d)) :
    ∑ t ∈ Finset.Icc 1 T, (wstar - w t) ⬝ᵥ u t ≤
      R / η + η * ∑ t ∈ Finset.Icc 1 T, ‖u t - u (t - 1)‖ ^ 2
        - (1 / (4 * η)) * ∑ t ∈ Finset.Icc 1 T, RegLearnGames.TotalRegret.l1 (w t - w (t - 1)) ^ 2 := by sorry

end RegLearnGames.IndivRegret
Source
Syrgkanis, Agarwal, Luo, Schapire, Fast Convergence of Regularized Learning in Games, arXiv:1507.00407v5, p. 5, Proposition 7 (R defined just above it); proof supp. pp. 2–5 (PDF pp. 11–14)
Human review
  • Endorsed by Shuze Chen · Oct 9, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 9, 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