Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 11.5, p. 183 — uniform-prior weighted average regret on exp-concave losses

Proved
ModernOnlineLearning.Aggregating.theorem_11_5

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

exp-concavityonline-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1regretweighted-average

Let V⊆RdV\subseteq\mathbb R^dV⊆Rd be convex, closed, bounded, and full-dimensional. Let α>0\alpha>0α>0, and suppose the losses ℓ1,…,ℓT\ell_1,\ldots,\ell_Tℓ1​,…,ℓT​ are α\alphaα-exp-concave on VVV. The Weighted Average Algorithm starts with the uniform distribution on VVV, sets λt=1/α\lambda_t=1/\alphaλt​=1/α, and predicts with the exponential-weighted mean xtx_txt​ of VVV based on losses before round ttt. For every u∈Vu\in Vu∈V,

∑t=1T(ℓt(xt)−ℓt(u))≤dα(1+ln⁡(Td+1)).\sum_{t=1}^{T}(\ell_t(x_t)-\ell_t(u))\leq\frac d\alpha\left(1+\ln\left(\frac Td+1\right)\right).t=1∑T​(ℓt​(xt​)−ℓt​(u))≤αd​(1+ln(dT​+1)).

The bound compares one deterministic sequence of weighted predictions with every fixed feasible competitor, with explicit dependence on dimension, horizon, and exp-concavity.

Formalization Note The theorem uses the published EWOO weighted-mean definition, which equals WAA for the uniform prior and λt=1/α\lambda_t=1/\alphaλt​=1/α. Rounds start at one. The hypotheses d,T≥1d,T\geq1d,T≥1, positive volume, almost-everywhere measurability on VVV, and integrability of the exponential weights and their vector moments make the divisions and Bochner integrals represent the source's quantities.


Retired 2026-10-27: a Lean-vs-paper fidelity audit found this statement weaker than, or narrower than, the cited result. A corrected statement will be resubmitted.

Preamble
import Mathlib
import Definitions.Def_LogRegretOCO_EWOO_ewooPoint
import Definitions.Def_ModernOnlineLearning_Aggregating_ExpConcave
set_option autoImplicit false

open MeasureTheory
Formal statement
namespace ModernOnlineLearning.Aggregating

/-- Theorem 11.5, p. 183: uniform-prior WAA with `1 / λ_t = α`.
The published EWOO point is exactly the uniform-prior WAA weighted mean. -/
theorem theorem_11_5 {d : ℕ} (hd : 0 < d) (T : ℕ) (hT : 0 < T)
    (V : Set (EuclideanSpace ℝ (Fin d)))
    (hconv : Convex ℝ V) (hclosed : IsClosed V) (hbounded : Bornology.IsBounded V)
    (hvol_pos : 0 < volume V)
    (α : ℝ) (hα : 0 < α)
    (ℓ : ℕ → EuclideanSpace ℝ (Fin d) → ℝ)
    (hexp : ∀ t ∈ Finset.Icc 1 T, ExpConcaveOn V α (ℓ t))
    (hmeas : ∀ t ∈ Finset.Icc 1 T, AEMeasurable (ℓ t) (volume.restrict V))
    (hint_weight : ∀ t ∈ Finset.Icc 1 T,
      IntegrableOn (LogRegretOCO.EWOO.ewooWeight α ℓ t) V)
    (hint_point : ∀ t ∈ Finset.Icc 1 T,
      IntegrableOn (fun x => LogRegretOCO.EWOO.ewooWeight α ℓ t x • x) V) :
    ∀ u ∈ V,
      (∑ t ∈ Finset.Icc 1 T,
          (ℓ t (LogRegretOCO.EWOO.ewooPoint V α ℓ t) - ℓ t u)) ≤
        (d : ℝ) / α * (1 + Real.log ((T : ℝ) / (d : ℝ) + 1)) := by sorry

end ModernOnlineLearning.Aggregating
Source
Orabona, arXiv:1912.13213v10, Theorem 11.5 and equation (11.6), p. 183; Algorithm 11.1, p. 180
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