Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 11, p. 5 — ‖uᵢ − uᵢ′‖²_* ≤ (n−1)Σ_{j≠i}‖wⱼ − wⱼ′‖² ≤ (n−1)²κ²

Proved
RegLearnGames.IndivRegret.theorem_11_variation_bound

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

no-regret-dynamicsnormal-form-gamesp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1regret

Consider an nnn-player game in which every player has ddd strategies and utilities ui(s)∈[0,1]u_i(s)\in[0,1]ui​(s)∈[0,1]. Let w=(w1,…,wn)w=(w_1,\dots,w_n)w=(w1​,…,wn​) and w′=(w1′,…,wn′)w'=(w'_1,\dots,w'_n)w′=(w1′​,…,wn′​) be two mixed profiles, and let κ\kappaκ bound every player's movement: ∥wj−wj′∥1≤κ\|w_j-w'_j\|_1\le\kappa∥wj​−wj′​∥1​≤κ for all jjj. Write uiu_iui​ and ui′u'_iui′​ for player iii's utility vectors against www and against w′w'w′. Then for every player iii,

∥ui−ui′∥∞2 ≤ (n−1)∑j≠i∥wj−wj′∥12 ≤ (n−1)2κ2.\|u_i-u'_i\|_\infty^2\ \le\ (n-1)\sum_{j\ne i}\|w_j-w'_j\|_1^2\ \le\ (n-1)^2\kappa^2 .∥ui​−ui′​∥∞2​ ≤ (n−1)j=i∑​∥wj​−wj′​∥12​ ≤ (n−1)2κ2.

Applied to consecutive profiles wt−1,wtw^{t-1},w^twt−1,wt of a repeated game, this bounds the variation of player iii's utilities by the movement of the other players; summed over t=1,…,Tt=1,\dots,Tt=1,…,T it turns the RVU property into the regret bound of Theorem 11.

Formalization Note The movement bound is assumed for every player jjj, including j=ij=ij=i, as in the stability property of Theorem 11, which holds for all players.

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

theorem theorem_11_variation_bound {n d : ℕ} (u : Fin n → (Fin n → Fin d) → ℝ)
    (hu : ∀ i s, u i s ∈ Set.Icc (0 : ℝ) 1)
    (w w' : Fin n → Fin d → ℝ)
    (hw : ∀ j, w j ∈ stdSimplex ℝ (Fin d)) (hw' : ∀ j, w' j ∈ stdSimplex ℝ (Fin d))
    (κ : ℝ) (hκ : ∀ j, RegLearnGames.TotalRegret.l1 (w j - w' j) ≤ κ) :
    ∀ i, ‖RegLearnGames.TotalRegret.utilVec u w i - RegLearnGames.TotalRegret.utilVec u w' i‖ ^ 2 ≤
        ((n : ℝ) - 1) * ∑ j ∈ Finset.univ.erase i, RegLearnGames.TotalRegret.l1 (w j - w' j) ^ 2 ∧
      ((n : ℝ) - 1) * ∑ j ∈ Finset.univ.erase i, RegLearnGames.TotalRegret.l1 (w j - w' j) ^ 2 ≤
        ((n : ℝ) - 1) ^ 2 * κ ^ 2 := by sorry

end RegLearnGames.IndivRegret
Source
Syrgkanis, Agarwal, Luo, Schapire, Fast Convergence of Regularized Learning in Games, arXiv:1507.00407v5, p. 5, §3.2, the display after Theorem 11 ("Similar reasoning as in Theorem 4 yields")
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