Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eq. (13): Burkholder's inequality for the noise sums of a Robbins–Monro algorithm

Proved
StochApproxDyn.MartingaleNoise.burkholder_eq13

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

inequalitiesmartingalesp2o-batch-pfp1ap2o-gran-per-chapterp2o-plan-paperp2o-v1stochastic-approximation

Fix a dimension ddd and an exponent q≥2q\ge2q≥2. There is a constant Cq>0C_q>0Cq​>0, depending only on qqq and ddd, with the following property. Let {xn}\{x_n\}{xn​}, given by (7), be a Robbins–Monro algorithm on a probability space (Ω,F,P)(\Omega,\mathcal F,P)(Ω,F,P) with filtration {Fn}\{\mathcal F_n\}{Fn​}, step sequence {γn}\{\gamma_n\}{γn​} and noise {Un}\{U_n\}{Un​} in Rd\mathbb R^dRd, with times τn\tau_nτn​ and inverse m(t)m(t)m(t). Then for every n≥0n\ge0n≥0 and every T>0T>0T>0

E{sup⁡n<k≤m(τn+T)∥∑i=nk−1γi+1Ui+1∥q}≤Cq E{[∑i=nm(τn+T)−1γi+12∥Ui+1∥2]q/2}.(13)E\Big\{\sup_{n<k\le m(\tau_n+T)}\Big\|\sum_{i=n}^{k-1}\gamma_{i+1}U_{i+1}\Big\|^q\Big\}\le C_q\,E\Big\{\Big[\sum_{i=n}^{m(\tau_n+T)-1}\gamma_{i+1}^2\|U_{i+1}\|^2\Big]^{q/2}\Big\}. \tag{13}E{n<k≤m(τn​+T)sup​​i=n∑k−1​γi+1​Ui+1​​q}≤Cq​E{[i=n∑m(τn​+T)−1​γi+12​∥Ui+1​∥2]q/2}.(13)

This is the instance of Burkholder's martingale inequality used in the proof of Proposition 4.2: the partial sums ∑i=nk−1γi+1Ui+1\sum_{i=n}^{k-1}\gamma_{i+1}U_{i+1}∑i=nk−1​γi+1​Ui+1​ form a martingale in kkk, and the right-hand side is the q/2q/2q/2-th moment of its square function.

Formalization Note Both expectations are integrals in [0,∞][0,\infty][0,∞] (either side may be +∞+\infty+∞). The supremum over an empty range (m(τn+T)≤nm(\tau_n+T)\le nm(τn​+T)≤n) is 000. The constant CqC_qCq​ is chosen before the probability space, the algorithm, nnn and TTT, so it is universal. The paper writes "for any t≥0t\ge0t≥0" before (13); the statement is about the index nnn and the window length TTT.

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

universe u

/-- Benaïm 1999, §4.2, proof of Proposition 4.2, Eq. (13), p. 15: the instance of Burkholder's
inequality used in the proof. For `q ≥ 2` there is a constant `C_q > 0` (depending only on `q`
and the dimension `d`) such that for every Robbins–Monro algorithm, every `n` and every `T > 0`,
`E sup_{n<k≤m(τ_n+T)} ‖∑_{i=n}^{k-1} γ_{i+1}U_{i+1}‖^q ≤ C_q E[(∑_{i=n}^{m(τ_n+T)-1} γ_{i+1}² ‖U_{i+1}‖²)^{q/2}]`. -/
theorem burkholder_eq13 (d : ℕ) (q : ℝ) (hq : 2 ≤ q) :
    ∃ C : ℝ, 0 < C ∧
      ∀ {Ω : Type u} {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)),
        IsRobbinsMonro P ℱ F γ x U →
        ∀ (n : ℕ) (T : ℝ), 0 < T →
          ∫⁻ ω, (Finset.Ioc n (stepIndex γ (StochApproxDyn.Interpolation.tau γ n + T))).sup
              (fun k => ‖∑ i ∈ Finset.Ico n k, γ (i + 1) • U (i + 1) ω‖ₑ ^ q) ∂P
            ≤ ENNReal.ofReal C *
              ∫⁻ ω, (∑ i ∈ Finset.Ico n (stepIndex γ (StochApproxDyn.Interpolation.tau γ n + T)),
                  ENNReal.ofReal (γ (i + 1) ^ 2) * ‖U (i + 1) ω‖ₑ ^ (2 : ℝ)) ^ (q / 2) ∂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. 15 (PDF p. 16), Eq. (13)
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