Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 6.10, p. 67 — three-part one-step OMD inequality

Proved
ModernOnlineLearning.OMD.lemma_6_10

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

bregman-divergenceonline-mirror-descentp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1regret

Under the assumptions of Lemma 6.10 and an online mirror descent run, let u∈Vu\in Vu∈V. On every round t=1,…,Tt=1,\ldots,Tt=1,…,T, with positive step size ηt\eta_tηt​ and selected subgradient gtg_tgt​,

ηt(ℓt(xt)−ℓt(u))≤ηt⟨gt,xt−u⟩≤Bψ(u;xt)−Bψ(u;xt+1)−Bψ(xt+1;xt)+ηt⟨gt,xt−xt+1⟩≤Bψ(u;xt)−Bψ(u;xt+1)+ηt22λ∥gt∥∗2.\begin{aligned} \eta_t(\ell_t(x_t)-\ell_t(u)) &\le \eta_t\langle g_t,x_t-u\rangle\\ &\le B_\psi(u;x_t)-B_\psi(u;x_{t+1})-B_\psi(x_{t+1};x_t) +\eta_t\langle g_t,x_t-x_{t+1}\rangle\\ &\le B_\psi(u;x_t)-B_\psi(u;x_{t+1}) +\frac{\eta_t^2}{2\lambda}\|g_t\|_*^2. \end{aligned}ηt​(ℓt​(xt​)−ℓt​(u))​≤ηt​⟨gt​,xt​−u⟩≤Bψ​(u;xt​)−Bψ​(u;xt+1​)−Bψ​(xt+1​;xt​)+ηt​⟨gt​,xt​−xt+1​⟩≤Bψ​(u;xt​)−Bψ​(u;xt+1​)+2ληt2​​∥gt​∥∗2​.​

This is the one-step estimate that telescopes to the regret bound in Theorem 6.11.

Formalization Note The primal norm is the norm on EEE, and ∥gt∥∗\|g_t\|_*∥gt​∥∗​ is the continuous dual's operator norm. Subgradient inequalities are relative to VVV. The setting assumes the book's condition (6.5) or (6.6); λ>0\lambda>0λ>0 and ηt>0\eta_t>0ηt​>0 make the displayed divisions meaningful. The update's existence and uniqueness are a separate item from this lemma.

Preamble
import Mathlib
import Definitions.Def_ModernOnlineLearning_OMD_Defs
Formal statement
namespace ModernOnlineLearning.OMD

/-- The full three-part one-step inequality in Lemma 6.10, p. 67, for every
round of Algorithm 6.1 under "(6.5) or (6.6)". -/
theorem lemma_6_10 {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E]
    [FiniteDimensional ℝ E] (X V : Set E) (ψ : E → ℝ) (lam : ℝ)
    (hsetting : IsOMDSetting X V ψ lam)
    (T : ℕ) (η : ℕ → ℝ) (ℓ : ℕ → E → ℝ)
    (x : ℕ → E) (g : ℕ → E →L[ℝ] ℝ)
    (hrun : IsOMDRun T X V ψ η ℓ x g) :
    ∀ t ∈ Finset.Icc 1 T, ∀ u ∈ V,
      η t * (ℓ t (x t) - ℓ t u) ≤ η t * g t (x t - u) ∧
      η t * g t (x t - u) ≤
        BeckTeboulleMD.EMDA.bregman ψ u (x t) -
        BeckTeboulleMD.EMDA.bregman ψ u (x (t + 1)) -
        BeckTeboulleMD.EMDA.bregman ψ (x (t + 1)) (x t) +
        η t * g t (x t - x (t + 1)) ∧
      BeckTeboulleMD.EMDA.bregman ψ u (x t) -
        BeckTeboulleMD.EMDA.bregman ψ u (x (t + 1)) -
        BeckTeboulleMD.EMDA.bregman ψ (x (t + 1)) (x t) +
        η t * g t (x t - x (t + 1)) ≤
        BeckTeboulleMD.EMDA.bregman ψ u (x t) -
        BeckTeboulleMD.EMDA.bregman ψ u (x (t + 1)) +
        (η t) ^ 2 / (2 * lam) * ‖g t‖ ^ 2 := by sorry

end ModernOnlineLearning.OMD
Source
Orabona, arXiv:1912.13213v10, Lemma 6.10, inequality clause, p. 67
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