Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 4, display after “so that”, p. 4 — Σᵢ‖uᵢ(w)−uᵢ(w′)‖²_* ≤ (n−1)ΣᵢΣ_{j≠i}‖wⱼ−w′ⱼ‖² = (n−1)²Σᵢ‖wᵢ−w′ᵢ‖²

Proved
RegLearnGames.TotalRegret.theorem_4_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-v1rvu-property

Consider an nnn-player game with ddd strategies per player and utilities ui(s)∈[0,1]u_i(s) \in [0,1]ui​(s)∈[0,1], and let w,w′w, w'w,w′ be two mixed profiles (every wj,wj′∈Δw_j, w'_j \in \Deltawj​,wj′​∈Δ). With ui(w)u_i(w)ui​(w) player iii's utility vector against w−iw_{-i}w−i​,

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

This is the variation bound of Theorem 4: the total squared movement of the utility vectors is at most (n−1)2(n-1)^2(n−1)2 times the total squared movement of the players' strategies. It is what lets the negative terms of the RVU property absorb the positive ones when β(n−1)2≤γ\beta (n-1)^2 \le \gammaβ(n−1)2≤γ.

Formalization Note Stated for two arbitrary mixed profiles; the paper applies it to wtw^twt and wt−1w^{t-1}wt−1. (n−1)(n-1)(n−1) is computed in R\mathbb RR.

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

theorem theorem_4_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)) :
    ∑ i, ‖utilVec u w i - utilVec u w' i‖ ^ 2 ≤
      ((n : ℝ) - 1) * ∑ i, ∑ j ∈ Finset.univ.erase i, l1 (w j - w' j) ^ 2 ∧
    ((n : ℝ) - 1) * ∑ i, ∑ j ∈ Finset.univ.erase i, l1 (w j - w' j) ^ 2 =
      ((n : ℝ) - 1) ^ 2 * ∑ i, l1 (w i - w' i) ^ 2 := by sorry

end RegLearnGames.TotalRegret
Source
Syrgkanis, Agarwal, Luo, Schapire, Fast Convergence of Regularized Learning in Games, arXiv:1507.00407v5, p. 4, proof of Theorem 4, display after “so that”
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