Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Equation (22), supp. p. 10 — aggregate first-order regret bound

Proved
RegLearnGames.FirstOrder.eq_22

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

algorithmic-game-theoryfirst-order-regretp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1smooth-games

Consider nnn players with d≥1d\ge1d≥1 strategies each and costs in [0,1][0,1][0,1]. Let wtw^twt be a mixed profile at each round through TTT. Suppose every player satisfies the first-order bound (21) with constants A1≥0A_1\ge0A1​≥0 and A2A_2A2​. For any fixed pure profile s∗s^*s∗, write P=∑t=1T∑ici,si∗tP=\sum_{t=1}^T\sum_i c^t_{i,s_i^*}P=∑t=1T​∑i​ci,si∗​t​. Then

∑t=1TC(wt)≤P+A1nlog⁡dP+A2nlog⁡d.\sum_{t=1}^T C(w^t)\le P+A_1\sqrt{n\log d}\sqrt P+A_2n\log d.t=1∑T​C(wt)≤P+A1​nlogd​P​+A2​nlogd.

This is the aggregate cost bound before the smoothness condition is used.

Formalization Note The source's Cauchy–Schwarz step requires A1≥0A_1\ge0A1​≥0, stated explicitly here. The printed final sum in (22) uses TTT as both bound and index; the index is read as ttt. The logloglog is natural logarithm.

Preamble
import Mathlib
import Definitions.Def_RegLearnGames_FirstOrder_Setting
Formal statement
namespace RegLearnGames.FirstOrder

open Finset

/-- The final line of display (22), after the sum over players. -/
theorem eq_22 {n d : ℕ} [NeZero d]
    (c : Fin n → (Fin n → Fin d) → ℝ)
    (hc : ∀ i s, c i s ∈ Set.Icc (0 : ℝ) 1)
    (w : ℕ → Fin n → Fin d → ℝ) (T : ℕ)
    (hw : ∀ t ∈ Finset.Icc 1 T, AGT.IsMixedProfile (w t))
    (A₁ A₂ : ℝ) (hA₁ : 0 ≤ A₁)
    (hreg : HasFirstOrderRegret c w T A₁ A₂)
    (sstar : Fin n → Fin d) :
    (∑ t ∈ Finset.Icc 1 T, socialCost c (w t)) ≤
      (∑ t ∈ Finset.Icc 1 T, ∑ i, costVec c (w t) i (sstar i)) +
        A₁ * Real.sqrt ((n : ℝ) * Real.log (d : ℝ)) *
          Real.sqrt (∑ t ∈ Finset.Icc 1 T,
            ∑ i, costVec c (w t) i (sstar i)) +
        A₂ * (n : ℝ) * Real.log (d : ℝ) := by sorry

end RegLearnGames.FirstOrder
Source
Syrgkanis, Agarwal, Luo, Schapire, Fast Convergence of Regularized Learning in Games, arXiv:1507.00407v5, supp. p. 10 (PDF p. 19), equation (22)
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