Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Smoothness step, supp. p. 10 — expected deviation cost is at most λOPT′ + µC(w)

Proved
RegLearnGames.FirstOrder.smoothness_step

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

algorithmic-game-theoryexpected-costp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1smooth-games

Let s∗s^*s∗ witness (λ,μ)(\lambda,\mu)(λ,μ)-smoothness: for every pure profile sss, the sum of costs incurred by players who each unilaterally switch to si∗s_i^*si∗​ is at most λOPT′+μC(s)\lambda\mathrm{OPT}'+\mu C(s)λOPT′+μC(s). For every mixed profile www,

∑ici,si∗(w)≤λOPT′+μC(w).\sum_i c_{i,s_i^*}(w)\le\lambda\mathrm{OPT}'+\mu C(w).i∑​ci,si∗​​(w)≤λOPT′+μC(w).

This transfers the pure-profile smoothness inequality to the independent mixed play generated during learning.

Formalization Note The Lean statement takes the explicit witness condition from equation (20), rather than an arbitrary unrelated profile. No sign assumptions on λ\lambdaλ or μ\muμ are needed for this expectation step.

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

open Finset

/-- Expected unilateral deviation costs are bounded by smoothness. -/
theorem smoothness_step {n d : ℕ} [NeZero d]
    (c : Fin n → (Fin n → Fin d) → ℝ)
    (w : Fin n → Fin d → ℝ) (hw : AGT.IsMixedProfile w)
    (lam mu : ℝ) (sstar : Fin n → Fin d)
    (hsmooth : ∀ s : Fin n → Fin d,
      (∑ i, c i (Function.update s i (sstar i))) ≤
        lam * optCost c + mu * socialCostPure c s) :
    (∑ i, costVec c w i (sstar i)) ≤
      lam * optCost c + mu * socialCost c w := 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), display after equation (22), beginning ‘By the smoothness assumption’
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