Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Section 4.2.3, p. 45 — implicit regret bound for self-bounded losses

Proved
ModernOnlineLearning.Adaptive.implicit_bound

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

online-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1regretself-bounded-loss

Under Theorem 4.30's assumptions, let xtx_txt​ be any adaptive OSD run on nonnegative, convex, sss-self-bounded losses over a nonempty closed convex set of diameter at most DDD. Then, for every u∈Vu\in Vu∈V,

Regret⁡T(u)≤2Ds∑t=1Tℓt(xt).\operatorname{Regret}_T(u)\le 2D\sqrt{s\sum_{t=1}^T\ell_t(x_t)}.RegretT​(u)≤2Dst=1∑T​ℓt​(xt​)​.

This is the implicit inequality preceding Lemma 4.29: the cumulative loss of the algorithm still appears on the right-hand side.

Formalization Note Self-boundedness is checked at every feasible point and for every full-space subgradient, with the loss infimum taken over all of Rd\mathbb R^dRd. Losses are real-valued and globally nonnegative; T≥1T\ge1T≥1 and s≥0s\ge0s≥0 are explicit.

Preamble
import Mathlib
import Definitions.Def_ModernOnlineLearning_Adaptive_Defs
Formal statement
namespace ModernOnlineLearning.Adaptive

/-- The implicit regret bound displayed immediately before Lemma 4.29 on p. 45. -/
theorem implicit_bound {d : ℕ} (V : Set (Vec d)) (ℓ : ℕ → Vec d → ℝ)
    (D s : ℝ) (T : ℕ) (x g : ℕ → Vec d)
    (hT : 1 ≤ T) (hs : 0 ≤ s) (hVne : V.Nonempty)
    (hVclosed : IsClosed V) (hVconv : Convex ℝ V)
    (hdiam : ∀ a ∈ V, ∀ b ∈ V, ‖a - b‖ ≤ D)
    (hconv : ∀ t ∈ Finset.Icc 1 T, ConvexOn ℝ Set.univ (ℓ t))
    (hnonneg : ∀ t ∈ Finset.Icc 1 T, ∀ z : Vec d, 0 ≤ ℓ t z)
    (hself : ∀ t ∈ Finset.Icc 1 T, IsSelfBounded V s (ℓ t))
    (hrun : IsAdaptiveOSDRun V ℓ D T x g) :
    ∀ u ∈ V, regret ℓ x u T ≤
      2 * D * Real.sqrt (s * (∑ t ∈ Finset.Icc 1 T, ℓ t (x t))) := by sorry

end ModernOnlineLearning.Adaptive
Source
Orabona, arXiv:1912.13213v10, §4.2.3, display before Lemma 4.29, p. 45
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