Proposition 2, p. 608 — liminf/limsup bounds on for nonnegative weights
ProvedStoneRegression.Criterion.proposition_2nonparametric-regressionp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1weight-functions
Let be i.i.d. -valued with law and let be a sequence of nonnegative Borel weights satisfying conditions (1)–(3) of Theorem 1. Suppose that there are sequences and of nonnegative constants such that
Let be a nonnegative Borel function on with . Then
and
The proposition controls the first moments of weighted sums by the total mass of the weights; Proposition 3 applies it to the squared weights in the step of Theorem 1.
Formalization Note. All expectations, limits inferior and superior are taken in (a of the may be ), with the convention of ; with both sides of the upper bound vanish. 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 2 (Stone 1977, p. 608). Nonnegative weights satisfying (1)–(3), constants `Mₙ, Nₙ ≥ 0` with
`P(Mₙ ≤ ∑ᵢ W_{ni}(X) ≤ Nₙ) → 1`, and a nonnegative Borel `f` with `Ef(X) < ∞`. Then
`liminf E ∑ᵢ W_{ni}(X) f(Xᵢ) ≥ (liminf Mₙ) Ef(X)` and `limsup E ∑ᵢ W_{ni}(X) f(Xᵢ) ≤ (limsup Nₙ) Ef(X)`,
all in `ℝ≥0∞` (the limits inferior and superior may be `+∞`). -/
theorem proposition_2 {d : ℕ} (μ : Measure (EuclideanSpace ℝ (Fin d))) [IsProbabilityMeasure μ]
(W : WeightSeq d) (hW : MeasurableWeights W) (hnn : Nonneg W)
(h1 : ∃ C : ℝ≥0, 1 ≤ C ∧ Cond1 μ W C) (h2 : ∃ D : ℝ, 1 ≤ D ∧ Cond2 μ W D) (h3 : Cond3 μ W)
(M N : ℕ → ℝ≥0)
(hMN : Tendsto (fun n => xLaw μ {ω | (M n : ℝ) ≤ ∑ i : Fin n, wAt W n ω i ∧
∑ i : Fin n, wAt W n ω i ≤ (N n : ℝ)}) atTop (𝓝 1))
(f : EuclideanSpace ℝ (Fin d) → ℝ≥0) (hf : Measurable f) (hfi : ∫⁻ x, f x ∂μ < ∞) :
liminf (fun n => (M n : ℝ≥0∞)) atTop * ∫⁻ x, f x ∂μ ≤
liminf (fun n => ∫⁻ ω, ∑ i : Fin n,
ENNReal.ofReal (wAt W n ω i) * (f (ω (i.val + 1)) : ℝ≥0∞) ∂(xLaw μ)) atTop ∧
limsup (fun n => ∫⁻ ω, ∑ i : Fin n,
ENNReal.ofReal (wAt W n ω i) * (f (ω (i.val + 1)) : ℝ≥0∞) ∂(xLaw μ)) atTop ≤
limsup (fun n => (N n : ℝ≥0∞)) atTop * ∫⁻ x, f x ∂μ := by sorry
end StoneRegression.Criterion
Source
Stone (1977), Ann. Statist. 5, Proposition 2, p. 608; proof p. 608
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.