Theorem 3.1, p. 17 — studentized coordinates and pairwise differences of the Lagrangian debiased estimator converge in distribution to N(0, 1)
ProvedLagrangeRank.Debias.theorem_3_1Work on one probability space . For each sample size let be the dimension, the random loss, the constraint defining , the true parameter, the initial estimator, an estimator of the inverse of and its (deterministic) target. Let be coordinates. Let
be the Lagrangian debiased estimator (3.9), with the block-inverse matrix of p. 16 built from , and the same formula at . Let ,
Assume:
- Assumptions 3.1–3.4 and the standing assumptions , (the structure
Assumptions), with fixed constants ; - , and ;
- Assumption 3.5: and for some and all , and
- , the entries of and are measurable.
Then
The theorem is the inferential core of the Lagrangian debiasing framework: it yields confidence intervals for single scores and for pairwise score differences under a general equality constraint, without inverting the (possibly singular) bordered Hessian.
Formalization Note. The paper's is read as "at most times the rate on events with ", with and independent of (this is the paper's ""). is read as the norm of , as in the proof of Corollary 3.1. The conditions are recalled in the proof (p. 43); is the standing assumption (p. 14); the variance lower bound is the condition under which Assumption 3.5 is stated; measurability is needed for convergence in distribution to make sense. The sample size, dimension and coordinates are sequences; all variables live on one probability space, and convergence in distribution is weak convergence of laws (TendstoInDistribution).
import Mathlib import Definitions.Def_LagrangeRank_Debias_Setting
namespace LagrangeRank.Debias
open MeasureTheory ProbabilityTheory Matrix Filter Topology
theorem theorem_3_1 {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))
(hclt1 : TendstoInDistribution (fun (n : ℕ) (ω : Ω) => 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 id (fun _ => P) (gaussianReal 0 1))
(hclt2 : TendstoInDistribution (fun (n : ℕ) (ω : Ω) => 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 id (fun _ => P) (gaussianReal 0 1))
(hmeas_hat : ∀ n, Measurable (thetaHat n))
(hmeas_Om : ∀ n a b, Measurable (fun ω => OmegaHat n ω a b))
(hmeas_grad : ∀ n, Measurable (fun ω => grad (L n ω) (thetaHat n ω))) :
TendstoInDistribution (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)))
atTop id (fun _ => P) (gaussianReal 0 1) ∧
TendstoInDistribution (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)))
atTop id (fun _ => P) (gaussianReal 0 1) := by sorry
end LagrangeRank.Debias
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.