Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eq. (17): ∑k≥0E(Δ(kT,T)q)<∞\sum_{k\ge0}E(\Delta(kT,T)^q)<\infty∑k≥0​E(Δ(kT,T)q)<∞

Proved
StochApproxDyn.MartingaleNoise.summable_eq17

by mikedeng1 · Oct 4, 2026 · Mathlib 0df444a (Lean v4.33.1)

martingalesp2o-batch-pfp1ap2o-gran-per-chapterp2o-plan-paperp2o-v1stochastic-approximation

Let {xn}\{x_n\}{xn​}, given by (7), be a Robbins–Monro algorithm with noise {Un}\{U_n\}{Un​} in Rd\mathbb R^dRd and step sequence {γn}\{\gamma_n\}{γn​}. Suppose that for some q≥2q\ge2q≥2

sup⁡nE(∥Un+1∥q)<∞and∑nγn1+q/2<∞.\sup_n E\big(\|U_{n+1}\|^q\big)<\infty\qquad\text{and}\qquad\sum_n\gamma_n^{1+q/2}<\infty .nsup​E(∥Un+1​∥q)<∞andn∑​γn1+q/2​<∞.

Then for every T>0T>0T>0

∑k≥0E(Δ(kT,T)q)<∞,(17)\sum_{k\ge0}E\big(\Delta(kT,T)^q\big)<\infty, \tag{17}k≥0∑​E(Δ(kT,T)q)<∞,(17)

where Δ(t,T)\Delta(t,T)Δ(t,T) is the noise deviation (10) of the realised noise path.

By the Borel–Cantelli lemma this gives Δ(kT,T)→0\Delta(kT,T)\to0Δ(kT,T)→0 almost surely as k→∞k\to\inftyk→∞.

Formalization Note The paper prints the chain ∑kE(Δ(kT,T)q)≤C(q,T)∫0∞γˉq/2(s) ds=∑γi+11+q/2<∞\sum_k E(\Delta(kT,T)^q)\le C(q,T)\int_0^\infty\bar\gamma^{q/2}(s)\,ds=\sum\gamma_{i+1}^{1+q/2}<\infty∑k​E(Δ(kT,T)q)≤C(q,T)∫0∞​γˉ​q/2(s)ds=∑γi+11+q/2​<∞, whose middle equality drops the factor C(q,T)C(q,T)C(q,T); only the finiteness is formalized. Expectations are integrals in [0,∞][0,\infty][0,∞] and the sum is the sum in [0,∞][0,\infty][0,∞]; the summability of γn+11+q/2\gamma_{n+1}^{1+q/2}γn+11+q/2​ is real summability of a nonnegative sequence.

Preamble
import Mathlib
import Definitions.Def_StochApproxDyn_MartingaleNoise_Interpolation
import Definitions.Def_StochApproxDyn_MartingaleNoise_AssumptionA1
import Definitions.Def_StochApproxDyn_MartingaleNoise_RobbinsMonro

open MeasureTheory ProbabilityTheory Filter Topology
open scoped ENNReal
Formal statement
namespace StochApproxDyn.MartingaleNoise

/-- Benaïm 1999, §4.2, proof of Proposition 4.2, Eq. (17), p. 16: under the hypotheses of
Proposition 4.2, for every `T > 0`, `∑_{k ≥ 0} E(Δ(kT, T)^q) < ∞`. -/
theorem summable_eq17 {d : ℕ} {Ω : Type*} {m0 : MeasurableSpace Ω}
    (P : Measure Ω) [IsProbabilityMeasure P] (ℱ : Filtration ℕ m0)
    (F : EuclideanSpace ℝ (Fin d) → EuclideanSpace ℝ (Fin d)) (γ : ℕ → ℝ)
    (x U : ℕ → Ω → EuclideanSpace ℝ (Fin d)) (hRM : IsRobbinsMonro P ℱ F γ x U)
    (q : ℝ) (hq : 2 ≤ q)
    (hmom : ∃ M : ℝ≥0∞, M < ⊤ ∧ ∀ n : ℕ, ∫⁻ ω, ‖U (n + 1) ω‖ₑ ^ q ∂P ≤ M)
    (hsum : Summable (fun n : ℕ => γ (n + 1) ^ (1 + q / 2))) :
    ∀ T : ℝ, 0 < T →
      ∑' k : ℕ, ∫⁻ ω, noiseDev γ (fun n => U n ω) ((k : ℝ) * T) T ^ q ∂P < ⊤ := by sorry

end StochApproxDyn.MartingaleNoise
Source
Benaïm, Dynamics of Stochastic Approximation Algorithms, Séminaire de Probabilités XXXIII, LNM 1709 (1999), DOI 10.1007/BFb0096509, Section 4.2, proof of Proposition 4.2, p. 16 (PDF p. 17), Eq. (17)
Human review
  • Endorsed by Shuze Chen · Oct 5, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 5, 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