Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§13.2.1, p. 214 — one-dimensional KT regret

Proved
ModernOnlineLearning.ParameterFree.kt_one_dim_regret

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

coin-bettingonline-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1parameter-free-regret

Run the one-dimensional KT OCO algorithm with ε>0\varepsilon>0ε>0 and L>0L>0L>0 for T≥1T\ge1T≥1 rounds. Each chosen subgradient gtg_tgt​ supports the loss ℓt\ell_tℓt​ at the prediction xtx_txt​ and satisfies ∣gt∣≤L|g_t|\le L∣gt​∣≤L. For every competitor u∈Ru\in\mathbb Ru∈R,

∑t=1T(ℓt(xt)−ℓt(u))≤∣u∣L2Tln⁡(1+e∣u∣Tε)+εL.\sum_{t=1}^T\bigl(\ell_t(x_t)-\ell_t(u)\bigr)\le |u|L\sqrt{2T\ln\left(1+\frac{e|u|T}{\varepsilon}\right)}+\varepsilon L.t=1∑T​(ℓt​(xt​)−ℓt​(u))≤∣u∣L2Tln(1+εe∣u∣T​)​+εL.

This per-coordinate guarantee is the direct input to the coordinate-wise bound.

Formalization Note The run also records full-space subdifferentiability of each loss. The positive-parameter and positive-horizon hypotheses make the displayed quotient and logarithm use their intended domains.

Preamble
import Mathlib
import Definitions.Def_ModernOnlineLearning_ParameterFree_Defs
Formal statement
namespace ModernOnlineLearning.ParameterFree

/-- The displayed one-dimensional KT regret guarantee in §13.2.1, p. 214. -/
theorem kt_one_dim_regret (ε L : ℝ) (hε : 0 < ε) (hL : 0 < L)
    (T : ℕ) (hT : 1 ≤ T) (ℓ : ℕ → ℝ → ℝ) (g x : ℕ → ℝ)
    (hrun : IsOneDKTRun ε L T ℓ g x) :
    ∀ u : ℝ,
      (∑ t ∈ Finset.Icc 1 T, (ℓ t (x t) - ℓ t u)) ≤
        |u| * L * Real.sqrt
          (2 * (T : ℝ) * Real.log (1 + Real.exp 1 * |u| * (T : ℝ) / ε)) + ε * L := by sorry

end ModernOnlineLearning.ParameterFree
Source
Orabona, arXiv:1912.13213v10, §13.2.1, displayed KT regret guarantee, p. 214
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