Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 4, display (2), p. 4 — ‖uᵢ(w)−uᵢ(w′)‖_* ≤ TV of the product of the others ≤ Σ_{j≠i}‖wⱼ−w′ⱼ‖₁

Proved
RegLearnGames.TotalRegret.display_2

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

normal-form-gamesp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1product-distributionstotal-variation

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]. 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 (every wj,wj′∈Δw_j, w'_j \in \Deltawj​,wj′​∈Δ), and fix a player iii. Write ui(w)u_i(w)ui​(w) for player iii's utility vector against w−iw_{-i}w−i​. Then

∥ui(w)−ui(w′)∥∞≤∑s−i∣∏j≠iwj,sj−∏j≠iwj,sj′∣≤∑j≠i∥wj−wj′∥1,\|u_i(w) - u_i(w')\|_\infty \le \sum_{s_{-i}} \Big|\prod_{j\ne i} w_{j,s_j} - \prod_{j \ne i} w'_{j,s_j}\Big| \le \sum_{j\ne i} \|w_j - w'_j\|_1,∥ui​(w)−ui​(w′)∥∞​≤s−i​∑​​j=i∏​wj,sj​​−j=i∏​wj,sj​′​​≤j=i∑​∥wj​−wj′​∥1​,

where the middle sum runs over all strategy choices s−i=(sj)j≠is_{-i} = (s_j)_{j \ne i}s−i​=(sj​)j=i​ of the players other than iii.

The middle quantity is (twice) the total variation distance between the two product distributions of the opponents' play; the second inequality is the subadditivity of total variation over product measures. In the paper it is applied with w=wtw = w^tw=wt and w′=wt−1w' = w^{t-1}w′=wt−1.

Formalization Note The index set {j≠i}\{j \ne i\}{j=i} is the subtype {j : Fin n // j ≠ i}; ∥⋅∥∞\|\cdot\|_\infty∥⋅∥∞​ is Mathlib's sup norm.

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

theorem display_2 {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 : Fin n) :
    ‖utilVec u w i - utilVec u w' i‖ ≤
        ∑ s : {j : Fin n // j ≠ i} → Fin d, |∏ j, w j.1 (s j) - ∏ j, w' j.1 (s j)| ∧
      ∑ s : {j : Fin n // j ≠ i} → Fin d, |∏ j, w j.1 (s j) - ∏ j, w' j.1 (s j)| ≤
        ∑ j : {j : Fin n // j ≠ i}, l1 (w j.1 - w' j.1) := 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, first display and display (2)
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