Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 14.2, p. 229 — summed OMD comparison before choosing the endpoint

Proved
ModernOnlineLearning.Dynamic.proof_14_2_sum

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

dynamic-regretmirror-descentonline-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1

Let T≥1T\ge1T≥1 and let x1,…,xT+1x_1,\ldots,x_{T+1}x1​,…,xT+1​ be an online mirror descent run with one positive step size η\etaη, a closed λ\lambdaλ-strongly convex regularizer ψ\psiψ, and subgradients gtg_tgt​. For any feasible comparator sequence u1,…,uT+1u_1,\ldots,u_{T+1}u1​,…,uT+1​, the summed inequality in the proof of Theorem 14.2 is

DRegret⁡T(u1,…,uT)≤Bψ(uT+1;x1)−Bψ(uT+1;xT+1)η+η2λ∑t=1T∥gt∥∗2+1η∑t=1T⟨∇ψ(xt+1)−∇ψ(x1),ut−ut+1⟩.\operatorname{DRegret}_T(u_1,\ldots,u_T)\le \frac{B_\psi(u_{T+1};x_1)-B_\psi(u_{T+1};x_{T+1})}{\eta} +\frac{\eta}{2\lambda}\sum_{t=1}^T\lVert g_t\rVert_*^2 +\frac1\eta\sum_{t=1}^T\langle\nabla\psi(x_{t+1})-\nabla\psi(x_1),u_t-u_{t+1}\rangle.DRegretT​(u1​,…,uT​)≤ηBψ​(uT+1​;x1​)−Bψ​(uT+1​;xT+1​)​+2λη​t=1∑T​∥gt​∥∗2​+η1​t=1∑T​⟨∇ψ(xt+1​)−∇ψ(x1​),ut​−ut+1​⟩.

Keeping uT+1u_{T+1}uT+1​ free exposes the comparator-shift term before the final specialization uT+1=uTu_{T+1}=u_TuT+1​=uT​.

Formalization Note The loss sequence has a relative subgradient at each feasible point, and the run's iterates through T+1T+1T+1 lie in V∩int⁡XV\cap\operatorname{int}XV∩intX. The extra comparator is feasible; no path-length bound has been applied yet.

Preamble
import Mathlib
import Definitions.Def_ModernOnlineLearning_Dynamic_Defs
Formal statement
namespace ModernOnlineLearning.Dynamic

/-- The display beginning “Putting everything together” in the proof of
Theorem 14.2, p. 229, before choosing `u (T+1) = u T`. -/
theorem proof_14_2_sum
    {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E] [FiniteDimensional ℝ E]
    (X V : Set E) (ψ : E → ℝ) (η : ℝ) (ℓ : ℕ → E → ℝ)
    (x u : ℕ → E) (g : ℕ → E →L[ℝ] ℝ) (T : ℕ) (lam : ℝ)
    (hT : 1 ≤ T) (hη : 0 < η) (hlam : 0 < lam)
    (hVsub : V ⊆ X) (hVne : V.Nonempty) (hVclosed : IsClosed V)
    (hVconv : Convex ℝ V) (hXconv : Convex ℝ X)
    (hψclosed : ClosedRegularizerOn X ψ)
    (hψstrict : StrictConvexOn ℝ X ψ)
    (hψdiff : DifferentiableOn ℝ ψ (interior X))
    (hψstrong : StrongConvexOn (V ∩ interior X) lam ψ)
    (hrun : IsOMDRun X V ψ (fun _ => η) ℓ x g T)
    (hu : ∀ t ∈ Finset.Icc 1 (T + 1), u t ∈ V) :
    dynamicRegret ℓ x u T ≤
      (BeckTeboulleMD.EMDA.bregman ψ (u (T + 1)) (x 1) -
        BeckTeboulleMD.EMDA.bregman ψ (u (T + 1)) (x (T + 1))) / η +
      (η / (2 * lam)) * (∑ t ∈ Finset.Icc 1 T, ‖g t‖ ^ 2) +
      (1 / η) * (∑ t ∈ Finset.Icc 1 T,
        (fderiv ℝ ψ (x (t + 1)) - fderiv ℝ ψ (x 1)) (u t - u (t + 1))) := by sorry

end ModernOnlineLearning.Dynamic
Source
Orabona, arXiv:1912.13213v10, proof of Theorem 14.2, display “Putting everything together”, p. 229 (PDF p. 241)
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