Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 20, supp. p. 4 — stability of optimistic FTRL: ‖wᵗ−gᵗ‖ ≤ η‖Mᵗ−uᵗ‖_* and ‖gᵗ−wᵗ⁺¹‖ ≤ η‖Mᵗ⁺¹‖_*

Proved
RegLearnGames.TotalRegret.lemma_20

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

online-learningoptimistic-ftrlp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1stability

Let Δ⊂Rd\Delta \subset \mathbb R^dΔ⊂Rd be the probability simplex, R\mathcal RR a regularizer that is 1-strongly convex with respect to ∥⋅∥1\|\cdot\|_1∥⋅∥1​ on Δ\DeltaΔ, and η>0\eta > 0η>0. Let u1,u2,…u^1, u^2, \dotsu1,u2,… and M1,M2,…M^1, M^2, \dotsM1,M2,… be arbitrary utility and predictor sequences in Rd\mathbb R^dRd, let w0,w1,…w^0, w^1, \dotsw0,w1,… be any run of optimistic FTRL and g0,g1,…g^0, g^1, \dotsg0,g1,… any leader sequence for them. Then for every t≥0t \ge 0t≥0,

∥wt−gt∥1≤η ∥Mt−ut∥∞and∥gt−wt+1∥1≤η ∥Mt+1∥∞.\|w^t - g^t\|_1 \le \eta\,\|M^t - u^t\|_\infty \qquad\text{and}\qquad \|g^t - w^{t+1}\|_1 \le \eta\,\|M^{t+1}\|_\infty.∥wt−gt∥1​≤η∥Mt−ut∥∞​and∥gt−wt+1∥1​≤η∥Mt+1∥∞​.

These two stability inequalities say that the iterate is close to the leader when the prediction is accurate, and that one step of the algorithm moves the leader by at most η\etaη times the size of the next prediction. Combined with Theorem 19 the first gives Proposition 7.

Formalization Note The paper writes the lemma for a general norm ∥⋅∥\|\cdot\|∥⋅∥ and its dual; here ∥⋅∥=∥⋅∥1\|\cdot\| = \|\cdot\|_1∥⋅∥=∥⋅∥1​ and ∥⋅∥∗=∥⋅∥∞\|\cdot\|_* = \|\cdot\|_\infty∥⋅∥∗​=∥⋅∥∞​. At t=0t = 0t=0 both w0w^0w0 and g0g^0g0 minimize R\mathcal RR over Δ\DeltaΔ (the values u0u^0u0, M0M^0M0 play no role in either sequence), so the first inequality holds there as well; it is stated for every ttt.

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

theorem lemma_20 {d : ℕ} (𝓡 : (Fin d → ℝ) → ℝ) (η : ℝ) (hη : 0 < η)
    (h𝓡 : IsOneStronglyConvexL1 𝓡)
    (M u w g : ℕ → Fin d → ℝ) (hw : IsOFTRL 𝓡 η M u w) (hg : IsLeader 𝓡 η u g) :
    ∀ t : ℕ, l1 (w t - g t) ≤ η * ‖M t - u t‖ ∧ l1 (g t - w (t + 1)) ≤ η * ‖M (t + 1)‖ := by sorry

end RegLearnGames.TotalRegret
Source
Syrgkanis, Agarwal, Luo, Schapire, Fast Convergence of Regularized Learning in Games, arXiv:1507.00407v5, supp. p. 4 (PDF p. 13), App. C, Lemma 20, (14)–(15)
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