Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 1, p. 607 — under (1)–(3), E∑i∣Wni(X)∣∣f(Xi)−f(X)∣r→0E\sum_i|W_{ni}(X)||f(X_i)-f(X)|^r\to0E∑i​∣Wni​(X)∣∣f(Xi​)−f(X)∣r→0

Proved
StoneRegression.Criterion.proposition_1

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

lp-convergencenonparametric-regressionp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1weight-functions

Let X,X1,X2,…X, X_1, X_2,\dotsX,X1​,X2​,… be i.i.d. Rd\mathbb R^dRd-valued with law μ\muμ and let {Wn}\{W_n\}{Wn​} be a sequence of Borel weights. Suppose that conditions (1)–(3) hold: there is C≥1C\ge1C≥1 with E∑i∣Wni(X)∣f(Xi)≤C Ef(X)E\sum_i|W_{ni}(X)|f(X_i)\le C\,Ef(X)E∑i​∣Wni​(X)∣f(Xi​)≤CEf(X) for every nonnegative Borel fff and n≥1n\ge1n≥1; there is D≥1D\ge1D≥1 with P(∑i∣Wni(X)∣≤D)=1P(\sum_i|W_{ni}(X)|\le D)=1P(∑i​∣Wni​(X)∣≤D)=1 for n≥1n\ge1n≥1; and ∑i∣Wni(X)∣ I{∥Xi−X∥>a}→0\sum_i|W_{ni}(X)|\,I_{\{\|X_i-X\|>a\}}\to0∑i​∣Wni​(X)∣I{∥Xi​−X∥>a}​→0 in probability for every a>0a>0a>0.

Let r≥1r\ge1r≥1 and let fff be a Borel function on Rd\mathbb R^dRd with E∣f(X)∣r<∞E|f(X)|^r<\inftyE∣f(X)∣r<∞. Then

lim⁡n→∞E∑i=1n∣Wni(X)∣ ∣f(Xi)−f(X)∣r=0.\lim_{n\to\infty} E\sum_{i=1}^n |W_{ni}(X)|\,|f(X_i)-f(X)|^r = 0 .n→∞lim​Ei=1∑n​∣Wni​(X)∣∣f(Xi​)−f(X)∣r=0.

This is the basic approximation step of the paper: weights concentrated near XXX reproduce f(X)f(X)f(X) in a weighted LrL^rLr sense. It feeds Propositions 2 and 5 and thereby the sufficiency half of Theorem 1.

Formalization Note. The expectation is a lower Lebesgue integral in [0,∞][0,\infty][0,∞] over the product law of (X,X1,X2,… )(X, X_1, X_2,\dots)(X,X1​,X2​,…); E∣f(X)∣r<∞E|f(X)|^r<\inftyE∣f(X)∣r<∞ is the corresponding lintegral against μ\muμ. Joint Borel measurability of the weights is the series' standing assumption.

Preamble
import Mathlib
import Definitions.Def_StoneRegression_Criterion_Setting

open MeasureTheory ProbabilityTheory Filter Topology
open scoped ENNReal NNReal BoundedContinuousFunction
Formal statement
namespace StoneRegression.Criterion

/-- Proposition 1 (Stone 1977, p. 607). Under (1)–(3), for `r ≥ 1` and a Borel `f` with `E|f(X)|ʳ < ∞`,
`E ∑ᵢ |W_{ni}(X)| |f(Xᵢ) − f(X)|ʳ → 0`. Sample indices are 0-based. -/
theorem proposition_1 {d : ℕ} (μ : Measure (EuclideanSpace ℝ (Fin d))) [IsProbabilityMeasure μ]
    (W : WeightSeq d) (hW : MeasurableWeights W)
    (h1 : ∃ C : ℝ≥0, 1 ≤ C ∧ Cond1 μ W C) (h2 : ∃ D : ℝ, 1 ≤ D ∧ Cond2 μ W D) (h3 : Cond3 μ W)
    (r : ℝ) (hr : 1 ≤ r) (f : EuclideanSpace ℝ (Fin d) → ℝ) (hf : Measurable f)
    (hfr : ∫⁻ x, ‖f x‖ₑ ^ r ∂μ < ∞) :
    Tendsto (fun n => ∫⁻ ω, ∑ i : Fin n,
        ‖wAt W n ω i‖ₑ * ‖f (ω (i.val + 1)) - f (ω 0)‖ₑ ^ r ∂(xLaw μ)) atTop (𝓝 0) := by sorry

end StoneRegression.Criterion
Source
Stone (1977), Ann. Statist. 5, Proposition 1, p. 607; proof pp. 607–608
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