Proof of Theorem 3.1, pp. 40–41, closing displays — studentized θ̂ᵈ equals minus the studentized score plus o_P(1)
ProvedLagrangeRank.Debias.asymptotic_linearityWork on one probability space . For each sample size let be the dimension, the random loss, the constraint, the true parameter, the initial estimator, the inverse-Hessian estimator and its target, and let be coordinates. Assume Assumptions 3.1–3.4 with the standing assumptions (the structure Assumptions, with rates , constants and events ), , , the scaling condition
and the variance lower bound of Assumption 3.5: for some and all , and . Then, in probability,
with , , the debiased estimator (3.9) and the block-inverse matrix of p. 16 at .
This is the "" step of the proof of Theorem 3.1; with Assumption 3.5 and Slutsky's lemma it gives the theorem.
Formalization Note. The page prints the normalization as , without the transpose that Theorem 3.1 and Assumption 3.5 carry; the theorem's normalization is used. is TendstoInMeasure to . The variance lower bound is the condition under which Assumption 3.5 is stated; it is needed to divide the remainder by .
import Mathlib import Definitions.Def_LagrangeRank_Debias_Setting
namespace LagrangeRank.Debias
open MeasureTheory ProbabilityTheory Matrix Filter Topology
theorem asymptotic_linearity {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω)
[IsProbabilityMeasure P]
(d : ℕ → ℕ) (L : (n : ℕ) → Ω → (Fin (d n) → ℝ) → ℝ) (f : (n : ℕ) → (Fin (d n) → ℝ) → ℝ)
(thetaStar : (n : ℕ) → Fin (d n) → ℝ) (thetaHat : (n : ℕ) → Ω → Fin (d n) → ℝ)
(OmegaHat : (n : ℕ) → Ω → Matrix (Fin (d n)) (Fin (d n)) ℝ)
(OmegaStar : (n : ℕ) → Matrix (Fin (d n)) (Fin (d n)) ℝ)
(r1 r2 r3 r4 r5 : ℕ → ℝ) (K c1 c2 c3 L1 L2 : ℝ) (E : ℕ → Set Ω)
(i j : (n : ℕ) → Fin (d n)) (hij : ∀ n, i n ≠ j n)
(hA : Assumptions P d L f thetaStar thetaHat OmegaHat OmegaStar
r1 r2 r3 r4 r5 K c1 c2 c3 L1 L2 E)
(hr1 : Tendsto r1 atTop (𝓝 0)) (hr4 : Tendsto r4 atTop (𝓝 0))
(hscale : Tendsto (fun n : ℕ => Real.sqrt (n : ℝ) *
(r1 n ^ 2 * r5 n + (r1 n + r4 n) * (r1 n ^ 2 + r2 n) + r1 n * r3 n)) atTop (𝓝 0))
(hvar : ∃ C : ℝ, 0 < C ∧ ∀ n,
C ≤ popVar P (L n) (f n) (OmegaStar n) (thetaStar n) (j n) ∧
C ≤ popVarPair P (L n) (f n) (OmegaStar n) (thetaStar n) (i n) (j n)) :
TendstoInMeasure P (fun (n : ℕ) (ω : Ω) =>
Real.sqrt (n : ℝ) *
(estThetaD (L n ω) (f n) (OmegaHat n ω) (thetaHat n ω) (j n) - thetaStar n (j n))
/ Real.sqrt (popVar P (L n) (f n) (OmegaStar n) (thetaStar n) (j n))
+ Real.sqrt (n : ℝ) *
(thetaStar11 (f n) (OmegaStar n) (thetaStar n) *ᵥ grad (L n ω) (thetaStar n)) (j n)
/ Real.sqrt (popVar P (L n) (f n) (OmegaStar n) (thetaStar n) (j n))) atTop 0 ∧
TendstoInMeasure P (fun (n : ℕ) (ω : Ω) =>
Real.sqrt (n : ℝ) *
((estThetaD (L n ω) (f n) (OmegaHat n ω) (thetaHat n ω) (i n) - thetaStar n (i n))
- (estThetaD (L n ω) (f n) (OmegaHat n ω) (thetaHat n ω) (j n) - thetaStar n (j n)))
/ Real.sqrt (popVarPair P (L n) (f n) (OmegaStar n) (thetaStar n) (i n) (j n))
+ Real.sqrt (n : ℝ) *
((thetaStar11 (f n) (OmegaStar n) (thetaStar n) *ᵥ grad (L n ω) (thetaStar n)) (i n)
- (thetaStar11 (f n) (OmegaStar n) (thetaStar n) *ᵥ grad (L n ω) (thetaStar n)) (j n))
/ Real.sqrt (popVarPair P (L n) (f n) (OmegaStar n) (thetaStar n) (i n) (j n)))
atTop 0 := by sorry
end LagrangeRank.Debias
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.