Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 3.10 — the adaptive-prediction concentration step

Proved
ModernOnlineLearning.OnlineToBatch.martingale_step_3_10

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

concentrationonline-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1probability

Draw T≥1T\ge1T≥1 samples independently from ρ\rhoρ. Let f(x,z)∈[0,1]f(x,z)\in[0,1]f(x,z)∈[0,1] be measurable in zzz for every x∈Vx\in Vx∈V, and let the deterministic online rule AAA predict xt∈Vx_t\in Vxt​∈V using only samples before round ttt. Put F(x)=Ez∼ρ[f(x,z)]F(x)=\mathbb E_{z\sim\rho}[f(x,z)]F(x)=Ez∼ρ​[f(x,z)]. For 0<δ<10<\delta<10<δ<1, with probability at least 1−δ/21-\delta/21−δ/2,

1T∑t=1TF(xt)≤1T∑t=1Tf(xt,ξt)+2ln⁡(2/δ)T.\frac1T\sum_{t=1}^T F(x_t)\le\frac1T\sum_{t=1}^T f(x_t,\xi_t)+\sqrt{\frac{2\ln(2/\delta)}{T}}.T1​t=1∑T​F(xt​)≤T1​t=1∑T​f(xt​,ξt​)+T2ln(2/δ)​​.

This is the first concentration bound in the proof of Theorem 3.10, for the sample-dependent predictions.

Formalization Note The sample space is the infinite product of ρ\rhoρ, and probabilities are real-valued. Measurability of each prediction, realized loss, and realized true risk is stated explicitly so the event and integrals are genuine.

Preamble
import Mathlib
import Definitions.Def_ModernOnlineLearning_OnlineToBatch_Defs
Formal statement
namespace ModernOnlineLearning.OnlineToBatch

/-- Orabona, arXiv:1912.13213v10, §3.1.2, first concentration display in the proof
of Theorem 3.10, p. 28. -/
theorem martingale_step_3_10 (d : ℕ) {D : Type*} [MeasurableSpace D]
    (ρ : MeasureTheory.Measure D) [MeasureTheory.IsProbabilityMeasure ρ]
    (V : Set (Decision d)) (f : Decision d → D → ℝ) (A : ℕ → (ℕ → D) → Decision d)
    (T : ℕ) (δ : ℝ)
    (hT : 1 ≤ T) (hδ0 : 0 < δ) (hδ1 : δ < 1)
    (hf_meas : ∀ x ∈ V, Measurable (f x))
    (hf_bounds : ∀ x ∈ V, ∀ z, 0 ≤ f x z ∧ f x z ≤ 1)
    (hA : IsOnlineAlgorithm V A)
    (hA_meas : ∀ t ∈ Finset.Icc 1 T, Measurable (A t))
    (hloss_meas : ∀ t ∈ Finset.Icc 1 T,
      Measurable (fun ω : ℕ → D => f (A t ω) (ω t)))
    (hrisk_meas : ∀ t ∈ Finset.Icc 1 T,
      Measurable (fun ω : ℕ → D => risk ρ f (A t ω))) :
    (MeasureTheory.Measure.infinitePi (fun _ : ℕ => ρ)).real
      {ω : ℕ → D |
        (∑ t ∈ Finset.Icc 1 T, risk ρ f (A t ω)) / (T : ℝ) ≤
          (∑ t ∈ Finset.Icc 1 T, f (A t ω) (ω t)) / (T : ℝ) +
            Real.sqrt (2 * Real.log (2 / δ) / (T : ℝ))} ≥ 1 - δ / 2 := by sorry

end ModernOnlineLearning.OnlineToBatch
Source
Orabona, arXiv:1912.13213v10, §3.1.2, proof of Theorem 3.10, p. 28 (PDF p. 40), display after “Thus, with probability at least 1 − δ/2”
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