Proposition 5, p. 609 — under (1)–(4), in
ProvedStoneRegression.Criterion.proposition_5lp-convergencenonparametric-regressionp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1weight-functions
Let be i.i.d. -valued with law and let be a sequence of Borel weights satisfying conditions (1)–(4) of Theorem 1: (1) with some , (2) with some , the localization condition (3), and in probability (4).
If and is a Borel function on with , then in :
This is the noise-free version of consistency: with it handles the bias part of in the proof of Theorem 1.
Formalization Note. The distance is a lower Lebesgue integral in , as is . Weights are assumed jointly Borel (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 5 (Stone 1977, p. 609). Under (1)–(4), for `r ≥ 1` and a Borel `f` with `E|f(X)|ʳ < ∞`,
`∑ᵢ W_{ni}(X) f(Xᵢ) → f(X)` in `Lʳ`, i.e. `E|∑ᵢ W_{ni}(X) f(Xᵢ) − f(X)|ʳ → 0`. -/
theorem proposition_5 {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)
(h4 : Cond4 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 * 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 5, p. 609
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.