Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Equation (12.2) — split linearized regret at the unconstrained prediction

Proved
ModernOnlineLearning.Reductions.eq_12_2

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

online-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1reductionregret

In a projected run of Algorithm 12.1, let u∈Vu\in Vu∈V be fixed and let gtg_tgt​ satisfy the subgradient inequality for ℓt\ell_tℓt​ at xtx_txt​ on VVV. For T≥1T\ge1T≥1,

∑t=1T(ℓt(xt)−ℓt(u))≤∑t=1Tgt(xt−u)=∑t=1T(gt(zt−u)+gt(xt−zt)).\sum_{t=1}^{T}(\ell_t(x_t)-\ell_t(u))\le\sum_{t=1}^{T}g_t(x_t-u)=\sum_{t=1}^{T}\bigl(g_t(z_t-u)+g_t(x_t-z_t)\bigr).t=1∑T​(ℓt​(xt​)−ℓt​(u))≤t=1∑T​gt​(xt​−u)=t=1∑T​(gt​(zt​−u)+gt​(xt​−zt​)).

This isolates the term that the surrogate loss must compensate when ztz_tzt​ lies outside VVV.

Formalization Note The loss subgradient inequality is restricted to VVV, which suffices because the comparator lies in VVV. The ambient space is finite-dimensional, and the book's round index starts at one.

Preamble
import Mathlib
import Definitions.Def_ModernOnlineLearning_Reductions_Setting
Formal statement
namespace ModernOnlineLearning.Reductions

/-- Orabona, equation (12.2), p. 196: first-order ModernOnlineLearning.OGD.regret and its split at `z_t`. -/
theorem eq_12_2 {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E]
    [FiniteDimensional ℝ E] (V W : Set E) (hV : V.Nonempty)
    (hclosed : IsClosed V) (hconv : Convex ℝ V) (hVW : V ⊆ W)
    (loss : ℕ → E → ℝ) (z x : ℕ → E) (g q : ℕ → E →L[ℝ] ℝ)
    (T : ℕ) (hT : 1 ≤ T) (hRun : IsProjectedRun V W loss z x g q T)
    (u : E) (hu : u ∈ V) :
    ModernOnlineLearning.OGD.regret loss x u T ≤ ∑ t ∈ Finset.Icc 1 T, g t (x t - u) ∧
      (∑ t ∈ Finset.Icc 1 T, g t (x t - u)) =
        ∑ t ∈ Finset.Icc 1 T, (g t (z t - u) + g t (x t - z t)) := by sorry

end ModernOnlineLearning.Reductions
Source
Orabona, arXiv:1912.13213v10, equation (12.2), proof of Theorem 12.5, p. 196
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