Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(23)–(24), p. 403 — d_n ≥ k̄_n b_n, k̄_n = inf (M(x) − α)/(x − θ) over 0 < |x − θ| ≤ A_n

Proved
RobbinsMonroSA.Conv.eq_24

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

p2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1robbins-monrostochastic-approximation

Under (4) with constant C>0C > 0C>0, (5), positive step sizes an>0a_n > 0an​>0, and the process (7)–(8), let

kˉn=inf⁡[M(x)−αx−θ]for 0<∣x−θ∣≤An.(23)\bar k_n = \inf\Big[\frac{M(x) - \alpha}{x - \theta}\Big] \quad\text{for } 0 < |x - \theta| \le A_n. \tag{23}kˉn​=inf[x−θM(x)−α​]for 0<∣x−θ∣≤An​.(23)

Then for every nnn,

dn≥kˉn bn.(24)d_n \ge \bar k_n\, b_n. \tag{24}dn​≥kˉn​bn​.(24)

Hence the particular sequence {kˉn}\{\bar k_n\}{kˉn​} satisfies the first part of (19) in Lemma 1.

Formalization Note Indices are 0-based (bigA … n is the paper's An+1A_{n+1}An+1​). The infimum is not formed in Lean: the statement says that every lower bound kkk of (M(z)−α)/(z−θ)(M(z)-\alpha)/(z-\theta)(M(z)−α)/(z−θ) on 0<∣z−θ∣≤An0<|z-\theta|\le A_n0<∣z−θ∣≤An​ satisfies dn≥k bnd_n \ge k\, b_ndn​≥kbn​. Since kˉn\bar k_nkˉn​ is the greatest such lower bound, this is equivalent to (24) (with bn≥0b_n \ge 0bn​≥0), and it also covers the case of an empty range (An=0A_n = 0An​=0, where the infimum is +∞+\infty+∞ and Lean's real infimum would be 000).

Preamble
import Mathlib
import Definitions.Def_RobbinsMonroSA_Conv_Setting

open MeasureTheory ProbabilityTheory Filter Topology
Formal statement
namespace RobbinsMonroSA.Conv

/-- (23)–(24), p. 403, in lower-bound form. If `k` bounds `(M(z) - α)/(z - θ)` from below on
`0 < |z - θ| ≤ A_n` (so `k ≤ k̄_n`, the infimum of (23)), then `d_n ≥ k b_n`. -/
theorem eq_24 {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω) [IsProbabilityMeasure P]
    (H : Kernel ℝ ℝ) [IsMarkovKernel H] (C : ℝ) (h4 : BoundedResponse H C) (α θ : ℝ)
    (a : ℕ → ℝ) (x1 : ℝ) (x y : ℕ → Ω → ℝ) (hxy : IsRMProcess P H a α x1 x y)
    (h5 : CrossesAt (regressionFn H) α θ) (hpos : ∀ n, 0 < a n) :
    ∀ n, ∀ k : ℝ,
      (∀ z : ℝ, 0 < |z - θ| → |z - θ| ≤ bigA x1 θ C α a n →
        k ≤ (regressionFn H z - α) / (z - θ)) →
      k * msd P x θ n ≤ dSeq P H α θ x n := by sorry

end RobbinsMonroSA.Conv
Source
Robbins and Monro, A stochastic approximation method, Ann. Math. Statist. 22 (1951), p. 403, (23)–(24)
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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