Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Quadratic inequality, supp. p. 10 — cost bound after introducing x

Proved
RegLearnGames.FirstOrder.quadratic_inequality

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

In the finite cost game of Theorem 23, suppose costs lie in [0,1][0,1][0,1], 0<μ<10<\mu<10<μ<1, the game is (λ,μ)(\lambda,\mu)(λ,μ)-smooth, the play through T≥1T\ge1T≥1 is mixed, and the first-order bound (21) holds with A1≥0A_1\ge0A1​≥0. Set

x=λTOPT′+μ∑t=1TC(wt).x=\sqrt{\lambda T\mathrm{OPT}'+\mu\sum_{t=1}^T C(w^t)}.x=λTOPT′+μt=1∑T​C(wt)​.

Then

x2−λTOPT′μ≤x2+A1nlog⁡d x+A2nlog⁡d.\frac{x^2-\lambda T\mathrm{OPT}'}{\mu}\le x^2+A_1\sqrt{n\log d}\,x+A_2n\log d.μx2−λTOPT′​≤x2+A1​nlogd​x+A2​nlogd.

This is the paper's inequality from which its quadratic bound on xxx follows.

Formalization Note The assumptions 0<μ<10<\mu<10<μ<1 and T≥1T\ge1T≥1 make the theorem's divisions meaningful; A1≥0A_1\ge0A1​≥0 is needed by the preceding Cauchy–Schwarz step. Smoothness and nonnegative costs imply that the expression under the square root is nonnegative. The paper writes both log and ln; both mean the natural logarithm.

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

open Finset

/-- The quadratic inequality on the quantity `x` defined in Appendix H. -/
theorem quadratic_inequality {n d : ℕ} [NeZero d]
    (c : Fin n → (Fin n → Fin d) → ℝ)
    (hc : ∀ i s, c i s ∈ Set.Icc (0 : ℝ) 1)
    (lam mu : ℝ) (hmu₀ : 0 < mu) (hmu₁ : mu < 1)
    (hsmooth : IsSmoothCost c lam mu)
    (A₁ A₂ : ℝ) (hA₁ : 0 ≤ A₁)
    (T : ℕ) (hT : 1 ≤ T)
    (w : ℕ → Fin n → Fin d → ℝ)
    (hw : ∀ t ∈ Finset.Icc 1 T, AGT.IsMixedProfile (w t))
    (hreg : HasFirstOrderRegret c w T A₁ A₂) :
    let x : ℝ := Real.sqrt (lam * (T : ℝ) * optCost c +
      mu * (∑ t ∈ Finset.Icc 1 T, socialCost c (w t)))
    (1 / mu) * (x ^ 2 - lam * (T : ℝ) * optCost c) ≤
      x ^ 2 + A₁ * Real.sqrt ((n : ℝ) * Real.log (d : ℝ)) * x +
        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), quadratic display following 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