Stat.Nonparametric.HOIF

Higher-order influence-function machinery for localized nonparametric functionals: product remainders, degenerate U-statistic variance, projected-kernel trace identities, and projection-risk assembly.

Degenerate­UStat­Variance 2 core · 2 supporting Variance bounds for degenerate rank-2 U-statistic terms in higher-order influence-function estimators. ★ degenerate_uStatistic_variance★ degenerate_uStatistic_variance_le

Variance of the degenerate (rank-2) U-statistic: the J/(nh)² term

Variance bounds for degenerate rank-2 U-statistic terms in higher-order influence-function estimators.

The order-m HOIF estimator's stochastic term is dominated by a degenerate order-2 U-statistic whose kernel is a J-dimensional, bandwidth-h localized projection. For such a kernel g (∫ g(x,·) dP = 0, symmetric, square-integrable) the off-diagonal second-moment computation of Causalean.Stat.UStatistic.Variance (integral_offDiag_sum_sq) gives the exact variance

Var[Uₙ] = 2ζ / (n(n−1)), ζ = ∬ g² dP dP.

When the localized projection kernel has L²-energy ζ ≤ C·J/h², this yields the HOIF degenerate U-statistic variance bound

Var[Uₙ] ≤ 4C·J / (nh)²,

the O(J/(nh)²) term of the projection-risk decomposition. The sibling HOIF.ProjectedKernelTrace file supplies the algebraic inverse-Gram trace identity ζ = J for the unlocalized projected kernel; the bandwidth-localized inequality is the hypothesis passed to degenerate_uStatistic_variance_le.

theorem degenerate_uStatistic_variance reviewed
Causalean.Stat.Nonparametric.HOIF

Exact variance of the degenerate order-2 U-statistic. For an i.i.d. sample S, if the kernel g is symmetric, square-integrable, and doubly degenerate — its conditional expectation given either argument vanishes — and the sample size n is at least 2, then the order-2 U-statistic built from g on n observations has variance Var[Uₙ] = 2ζ / (n(n−1)), where ζ = ∬ g² dP dP.

Formal statement
S :
IIDSample Ω X μ P
hg :
n :
hn :
2 ≤ n
variance (uStatistic S g n) μ = 2 * IIDSample.zeta P g / ((n : ℝ) * ((n : ℝ) - 1))
Proof (Lean source)
theorem degenerate_uStatistic_variance (S : IIDSample Ω X μ P) (hg : DegenKernel P g) {n : ℕ} (hn : 2 ≤ n) : variance (uStatistic S g n) μ = 2 * IIDSample.zeta P g / ((n : ℝ) * ((n : ℝ) - 1)) := by have hn0 : (0 : ℝ) < (n : ℝ) := by exact_mod_cast (by omega : 0 < n) have hmem : MemLp (uStatistic S g n) 2 μ := memLp_uStatistic S hg hn have hmean : ∫ ω, uStatistic S g n ω ∂μ = 0 := integral_uStatistic_eq_zero S hg hn -- Second moment from the √n-rescaled identity: ∫ (√n Uₙ)² = n · ∫ Uₙ² = 2ζ/(n−1). have hsq : ∫ ω, (uStatistic S g n ω) ^ 2 ∂μ = 2 * IIDSample.zeta P g / ((n : ℝ) * ((n : ℝ) - 1)) := by have hres := S.integral_rescaled_sq hg hn have hpoint : (fun ω => (sqrt (n : ℝ) * uStatistic S g n ω) ^ 2) = (fun ω => (n : ℝ) * (uStatistic S g n ω) ^ 2) := by funext ω; rw [mul_pow, Real.sq_sqrt (le_of_lt hn0)] rw [hpoint, integral_const_mul] at hres have hne : (n : ℝ) ≠ 0 := ne_of_gt hn0 have hn1 : (n : ℝ) - 1 ≠ 0 := by have : (2 : ℝ) ≤ (n : ℝ) := by exact_mod_cast hn intro h; linarith field_simp at hres ⊢ linarith [hres] rw [ProbabilityTheory.variance_eq_sub hmem, hmean] simp only [ne_eq, OfNat.ofNat_ne_zero, not_false_eq_true, zero_pow, sub_zero] exact hsq
Causalean.Stat.Nonparametric.HOIF.degenerate_uStatistic_variance · Causalean/Stat/Nonparametric/HOIF/DegenerateUStatVariance.lean:66 · uses DegenKernel , IIDSample , zeta , uStatistic
theorem degenerate_uStatistic_variance_le reviewed
Causalean.Stat.Nonparametric.HOIF

HOIF degenerate U-statistic variance bound O(J/(nh)²). For an i.i.d. sample S, if the kernel g is symmetric, square-integrable, and doubly degenerate, the sample size n is at least 2, the bandwidth h is positive, the projection dimension J is nonnegative, the trace constant C is nonnegative, and the localized, J-dimensional projection kernel g has L²-energy ζ = ∬ g² dP dP bounded by C·J/h², then the degenerate order-2 U-statistic's variance satisfies Var[Uₙ] ≤ 4C·J / (nh)².

Formal statement
S :
IIDSample Ω X μ P
hg :
C J h :
n :
hn :
2 ≤ n
hh :
0 < h
hJ :
0 ≤ J
hC :
0 ≤ C
hzeta :
IIDSample.zeta P g ≤ C * J / h ^ 2
variance (uStatistic S g n) μ ≤ 4 * C * J / ((n : ℝ) * h) ^ 2
Proof (Lean source)
theorem degenerate_uStatistic_variance_le (S : IIDSample Ω X μ P) (hg : DegenKernel P g) {C J h : ℝ} {n : ℕ} (hn : 2 ≤ n) (hh : 0 < h) (hJ : 0 ≤ J) (hC : 0 ≤ C) (hzeta : IIDSample.zeta P g ≤ C * J / h ^ 2) : variance (uStatistic S g n) μ ≤ 4 * C * J / ((n : ℝ) * h) ^ 2 := by have hn0 : (0 : ℝ) < (n : ℝ) := by exact_mod_cast (by omega : 0 < n) have hn2 : (2 : ℝ) ≤ (n : ℝ) := by exact_mod_cast hn have hnm1 : (0 : ℝ) < (n : ℝ) - 1 := by linarith have hζnn : 0 ≤ IIDSample.zeta P g := IIDSample.zeta_nonneg rw [degenerate_uStatistic_variance S hg hn] have hprodpos : 0 < (n : ℝ) * ((n : ℝ) - 1) := mul_pos hn0 hnm1 have hnhpos : 0 < ((n : ℝ) * h) ^ 2 := by positivity have hh2 : 0 < h ^ 2 := by positivity have hCJ : 0 ≤ C * J := mul_nonneg hC hJ -- ζ·h² ≤ C·J (clear the denominator in the trace bound). have hζh2 : IIDSample.zeta P g * h ^ 2 ≤ C * J := (le_div_iff₀ hh2).mp hzeta rw [div_le_div_iff₀ hprodpos hnhpos] -- goal: 2ζ · (nh)² ≤ 4CJ · (n(n−1)) nlinarith [hζh2, hCJ, hn2, hh2, mul_nonneg hCJ (le_of_lt hn0), mul_le_mul_of_nonneg_left hζh2 (by positivity : (0:ℝ) ≤ (n:ℝ) ^ 2), mul_nonneg hCJ (sub_nonneg.mpr hn2)]
Causalean.Stat.Nonparametric.HOIF.degenerate_uStatistic_variance_le · Causalean/Stat/Nonparametric/HOIF/DegenerateUStatVariance.lean:99 · uses DegenKernel , IIDSample , zeta , uStatistic
2 supporting declarations (lemmas, instances)
Product­Remainder 1 core · 2 supporting The order-m higher-order influence function (HOIF) estimator removes the leading nuisance-estimation bias up to a remainder that is a *finite sum of products of m+1 nuisance L²-errors*. ★ hoif_order_choice_negligible

Order-m HOIF estimation bias: the product remainder

The order-m higher-order influence function (HOIF) estimator removes the leading nuisance-estimation bias up to a remainder that is a finite sum of products of m+1 nuisance -errors. Writing δ for the largest of those errors, every term of the remainder is a product of m+1 factors each ≤ δ, so the whole remainder is bounded by |T|·δ^{m+1} (with |T| the fixed number of terms), and its squared contribution by

R² ≤ |T|²·δ^{2(m+1)}.

This is the order-m analogue of the second-order doubly-robust remainder (product of two nuisance errors): pushing to order m buys the higher power δ^{m+1}. Choosing the order m so that 2(m+1)λ_* > the target risk exponent makes this squared contribution o(ρ_n) — the rate-selection lemma hoif_order_choice_negligible.

This file is purely elementary (finite products of bounded reals + a power-law limit); it carries no measure theory and is the leaf of the HOIF substrate.

theorem hoif_order_choice_negligible reviewed
Causalean.Stat.Nonparametric.HOIF

Rate selection: a high-enough HOIF order makes the squared remainder o(ρ_n). For a squared product-remainder bound of the power-law form K·n^{-a} and a target risk rate ρ_n = n^{-κ}, if the remainder's decay exponent a exceeds the target rate's exponent κ, then the ratio (K·n^{-a}) / n^{-κ} = K·n^{κ-a} tends to 0 as n → ∞: the HOIF estimation bias is asymptotically negligible relative to the target rate.

Formal statement
K a κ :
haκ :
κ < a
Tendsto (fun n : ℕ => K * (n : ℝ) ^ (κ - a)) atTop (𝓝 0)
Proof (Lean source)
theorem hoif_order_choice_negligible {K a κ : ℝ} (haκ : κ < a) : Tendsto (fun n : ℕ => K * (n : ℝ) ^ (κ - a)) atTop (𝓝 0) := by have hpos : 0 < a - κ := by linarith have hbase : Tendsto (fun n : ℕ => (n : ℝ)) atTop atTop := tendsto_natCast_atTop_atTop have hpow : Tendsto (fun x : ℝ => x ^ (-(a - κ))) atTop (𝓝 0) := tendsto_rpow_neg_atTop hpos have hcomp : Tendsto (fun n : ℕ => (n : ℝ) ^ (-(a - κ))) atTop (𝓝 0) := hpow.comp hbase have := hcomp.const_mul K simpa [neg_sub] using this
Causalean.Stat.Nonparametric.HOIF.hoif_order_choice_negligible · Causalean/Stat/Nonparametric/HOIF/ProductRemainder.lean:82
2 supporting declarations (lemmas, instances)
  • prod_le_pow_of_factors_le theorem — A product of m+1 factors each in [0, δ] is at most δ^{m+1}. Each nuisance-error factor of a single HOIF remainder term is nonnegative and bounded by the largest error δ; multiplying m+1 of them keeps the product below δ^{m+1}.
    ι :
    Type*
    e :
    ι → ℝ
    m :
    δ :
    s :
    Finset
    idx :
    ℕ → ι
    hcard :
    s.card = m + 1
    hnn :
    ∀ k ∈ s, 0 ≤ e (idx k)
    hle :
    ∀ k ∈ s, e (idx k) ≤ δ
    ∏ k ∈ s, e (idx k) ≤ δ ^ (m + 1)
    Proof (Lean source)
    theorem prod_le_pow_of_factors_le {ι : Type*} (e : ι → ℝ) (m : ℕ) (δ : ℝ) (s : Finset ℕ) (idx : ℕ → ι) (hcard : s.card = m + 1) (hnn : ∀ k ∈ s, 0 ≤ e (idx k)) (hle : ∀ k ∈ s, e (idx k) ≤ δ) : ∏ k ∈ s, e (idx k) ≤ δ ^ (m + 1) := by calc ∏ k ∈ s, e (idx k) ≤ ∏ _k ∈ s, δ := Finset.prod_le_prod (fun k hk => hnn k hk) (fun k hk => hle k hk) _ = δ ^ (m + 1) := by rw [Finset.prod_const, hcard]
    Causalean.Stat.Nonparametric.HOIF.prod_le_pow_of_factors_le · Causalean/Stat/Nonparametric/HOIF/ProductRemainder.lean:33
  • hoif_remainder_sq_le theorem — Squared HOIF product-remainder bound. The order-m HOIF estimation-bias remainder R is dominated by a sum, over a finite index set T of terms, of products of m+1 nuisance-error factors e t k; every factor lies in [0, δ], where δ is the largest nuisance L²-error. Then the remainder's squared contribution obeys R² ≤ |T|²·δ^{2(m+1)}. This is the order-m doubly-robust bound: the higher the order, the higher the power of δ.
    ι :
    Type*
    T :
    e :
    ι → ℕ → ℝ
    m :
    δ :
    R :
    hnn :
    ∀ t ∈ T, ∀ k ∈ range (m + 1), 0 ≤ e t k
    hle :
    ∀ t ∈ T, ∀ k ∈ range (m + 1), e t k ≤ δ
    hbound :
    |R| ≤ ∑ t ∈ T, ∏ k ∈ range (m + 1), e t k
    R ^ 2 ≤ (T.card : ℝ) ^ 2 * δ ^ (2 * (m + 1))
    Proof (Lean source)
    theorem hoif_remainder_sq_le {ι : Type*} (T : Finset ι) (e : ι → ℕ → ℝ) (m : ℕ) (δ : ℝ) (R : ℝ) (hnn : ∀ t ∈ T, ∀ k ∈ range (m + 1), 0 ≤ e t k) (hle : ∀ t ∈ T, ∀ k ∈ range (m + 1), e t k ≤ δ) (hbound : |R| ≤ ∑ t ∈ T, ∏ k ∈ range (m + 1), e t k) : R ^ 2 ≤ (T.card : ℝ) ^ 2 * δ ^ (2 * (m + 1)) := by -- Each term ≤ δ^{m+1}. have hterm : ∀ t ∈ T, ∏ k ∈ range (m + 1), e t k ≤ δ ^ (m + 1) := by intro t ht calc ∏ k ∈ range (m + 1), e t k ≤ ∏ _k ∈ range (m + 1), δ := Finset.prod_le_prod (fun k hk => hnn t ht k hk) (fun k hk => hle t ht k hk) _ = δ ^ (m + 1) := by rw [Finset.prod_const, Finset.card_range] -- Sum ≤ |T|·δ^{m+1}. have hsum_le : ∑ t ∈ T, ∏ k ∈ range (m + 1), e t k ≤ (T.card : ℝ) * δ ^ (m + 1) := by calc ∑ t ∈ T, ∏ k ∈ range (m + 1), e t k ≤ ∑ _t ∈ T, δ ^ (m + 1) := Finset.sum_le_sum hterm _ = (T.card : ℝ) * δ ^ (m + 1) := by rw [Finset.sum_const, nsmul_eq_mul] -- The sum is nonnegative (sum of products of nonnegatives). have hsum_nn : 0 ≤ ∑ t ∈ T, ∏ k ∈ range (m + 1), e t k := sum_nonneg (fun t ht => Finset.prod_nonneg (fun k hk => hnn t ht k hk)) -- Square the chain |R| ≤ sum ≤ |T|·δ^{m+1}. have hRabs : |R| ≤ (T.card : ℝ) * δ ^ (m + 1) := le_trans hbound hsum_le have hR2 : R ^ 2 ≤ ((T.card : ℝ) * δ ^ (m + 1)) ^ 2 := by rw [← sq_abs R] exact pow_le_pow_left₀ (abs_nonneg R) hRabs 2 calc R ^ 2 ≤ ((T.card : ℝ) * δ ^ (m + 1)) ^ 2 := hR2 _ = (T.card : ℝ) ^ 2 * δ ^ (2 * (m + 1)) := by rw [mul_pow, ← pow_mul, Nat.mul_comm (m + 1) 2]
    Causalean.Stat.Nonparametric.HOIF.hoif_remainder_sq_le · Causalean/Stat/Nonparametric/HOIF/ProductRemainder.lean:45
Projected­Kernel­Trace 3 core · 4 supporting Trace and degeneracy identities for projected HOIF kernels, showing that a rank-J projection kernel has L² energy equal to the projection dimension under inverse-Gram weighting. ★ projKernel_L2_eq_dim

The projected localized HOIF kernel: L²-energy equals the projection dimension

Trace and degeneracy identities for projected HOIF kernels, showing that a rank-J projection kernel has L² energy equal to the projection dimension under inverse-Gram weighting.

The order-2 stochastic term of the order-m HOIF estimator is a degenerate U-statistic whose kernel is the J-dimensional projection

g(x, y) = ⟨c(x), M c(y)⟩ = ∑_{k,l} c(x)_k · M_{kl} · c(y)_l,

where c : X → ℝ^J is the (bandwidth-localized, residual-weighted) basis evaluated at the covariate and M is the projection weighting matrix. Writing Σ = 𝔼[c cᵀ] for the second-moment (Gram) matrix, the L²-energy of the kernel factors, by the independence of the two sample points, into

ζ = ∬ g² dP dP = ∑_{k,l,k',l'} M_{kl} M_{k'l'} Σ_{kk'} Σ_{ll'} = tr(Σ M Σ Mᵀ).

With the natural HOIF weighting M = Σ⁻¹ this collapses to ζ = J — the projected degenerate kernel's L²-energy is exactly the projection dimension. In localized analyses this identity is paired with the separate bandwidth scaling hypothesis ζ ≤ C·J/h² used by Causalean.Stat.Nonparametric.HOIF.DegenerateUStatVariance (Var = 2ζ/(n(n−1))), this is the source of the O(J/(nh)²) term in the HOIF projection risk.

projKernel_degen records only the one-sided degeneracy field ∫ g(x,·) dP = 0 when the basis coordinates are centered (∫ c_l dP = 0). It does not by itself construct a DegenKernel, since that structure also carries measurability, symmetry, and square-integrability requirements.

def gram reviewed
Causalean.Stat.Nonparametric.HOIF

The second-moment (Gram) matrix of the basis c: Σ_{kl} = ∫ c(x)_k c(x)_l dP.

Definition (Lean source)
noncomputable def gram (c : X → Fin J → ℝ) (P : Measure X) : Matrix (Fin J) (Fin J) ℝ := of (fun k l => ∫ x, c x k * c x l ∂P)
def projKernel reviewed
Causalean.Stat.Nonparametric.HOIF

The projected HOIF kernel g(x,y) = ∑_{k,l} c(x)_k M_{kl} c(y)_l.

Definition (Lean source)
noncomputable def projKernel (c : X → Fin J → ℝ) (M : Matrix (Fin J) (Fin J) ℝ) : X → X → ℝ := fun x y => ∑ k, ∑ l, c x k * M k l * c y l
Causalean.Stat.Nonparametric.HOIF.projKernel · Causalean/Stat/Nonparametric/HOIF/ProjectedKernelTrace.lean:53
theorem projKernel_L2_eq_dim reviewed
Causalean.Stat.Nonparametric.HOIF

Projected degenerate-kernel L²-energy equals the dimension: ζ = J. For a feature map c into J-dimensional space, if every coordinate of c is square-integrable under P, the Gram matrix of c under P is invertible, and M is the inverse of that Gram matrix, then the squared L²(P⊗P)-norm of the HOIF projection kernel g(x,y) = ⟨c(x), M·c(y)⟩ equals the projection dimension J.

Formal statement
c :
X → Fin J → ℝ
M :
Matrix (Fin J) (Fin J) ℝ
hc :
∀ k, MemLp (fun x => c x k) 2 P
hu :
IsUnit (gram c P).det
hM :
M = (gram c P)⁻¹
∫ p, (projKernel c M p.1 p.2) ^ 2 ∂(P.prod P) = (J : ℝ)
Proof (Lean source)
theorem projKernel_L2_eq_dim (c : X → Fin J → ℝ) (M : Matrix (Fin J) (Fin J) ℝ) (hc : ∀ k, MemLp (fun x => c x k) 2 P) (hu : IsUnit (gram c P).det) (hM : M = (gram c P)⁻¹) : ∫ p, (projKernel c M p.1 p.2) ^ 2 ∂(P.prod P) = (J : ℝ) := by rw [projKernel_L2_eq_sum c M hc] exact sum_collapse_dim M (gram c P) hu hM
Causalean.Stat.Nonparametric.HOIF.projKernel_L2_eq_dim · Causalean/Stat/Nonparametric/HOIF/ProjectedKernelTrace.lean:215 · uses gram , projKernel
4 supporting declarations (lemmas, instances)
  • gram_symm theorem — The Gram matrix is symmetric.
    c :
    X → Fin J → ℝ
    (gram c P)ᵀ = gram c P
    Proof (Lean source)
    theorem gram_symm (c : X → Fin J → ℝ) : (gram c P)ᵀ = gram c P := by funext k l simp only [Matrix.transpose_apply, gram, Matrix.of_apply] simp_rw [mul_comm]
    Causalean.Stat.Nonparametric.HOIF.gram_symm · Causalean/Stat/Nonparametric/HOIF/ProjectedKernelTrace.lean:59
  • projKernel_degen theorem — One-sided degeneracy of the projected kernel. If the basis coordinates are centered (∫ c_l dP = 0 for every l), then ∫ g(x, ·) dP = 0 for every x. This records the zero-integral field only; measurability, symmetry, and square-integrability are separate requirements for packaging the kernel as a degenerate U-statistic kernel.
    c :
    X → Fin J → ℝ
    M :
    Matrix (Fin J) (Fin J) ℝ
    hint :
    ∀ l, Integrable (fun x => c x l) P
    hzero :
    ∀ l, ∫ x, c x l ∂P = 0
    x :
    X
    ∫ y, projKernel c M x y ∂P = 0
    Proof (Lean source)
    theorem projKernel_degen (c : X → Fin J → ℝ) (M : Matrix (Fin J) (Fin J) ℝ) (hint : ∀ l, Integrable (fun x => c x l) P) (hzero : ∀ l, ∫ x, c x l ∂P = 0) (x : X) : ∫ y, projKernel c M x y ∂P = 0 := by unfold projKernel rw [integral_finset_sum] · refine Finset.sum_eq_zero (fun k _ => ?_) rw [integral_finset_sum] · refine Finset.sum_eq_zero (fun l _ => ?_) have : (fun y => c x k * M k l * c y l) = (fun y => (c x k * M k l) * c y l) := by funext y; ring rw [this, integral_const_mul, hzero l, mul_zero] · intro l _ exact ((hint l).const_mul (c x k * M k l)) · intro k _ apply integrable_finset_sum intro l _ exact ((hint l).const_mul (c x k * M k l))
    Causalean.Stat.Nonparametric.HOIF.projKernel_degen · Causalean/Stat/Nonparametric/HOIF/ProjectedKernelTrace.lean:66
  • projKernel_L2_eq_sum theorem — L²-energy of the projected kernel (expanded form). By independence of the two sample points, the double integral of the squared projected kernel factors into Gram entries:
    c :
    X → Fin J → ℝ
    M :
    Matrix (Fin J) (Fin J) ℝ
    hc :
    ∀ k, MemLp (fun x => c x k) 2 P
    ∫ p, (projKernel c M p.1 p.2) ^ 2 ∂(P.prod P)
    = ∑ k, ∑ l, ∑ k', ∑ l', M k l * M k' l' * gram c P k k' * gram c P l l'
    Proof (Lean source)
    theorem projKernel_L2_eq_sum (c : X → Fin J → ℝ) (M : Matrix (Fin J) (Fin J) ℝ) (hc : ∀ k, MemLp (fun x => c x k) 2 P) : ∫ p, (projKernel c M p.1 p.2) ^ 2 ∂(P.prod P) = ∑ k, ∑ l, ∑ k', ∑ l', M k l * M k' l' * gram c P k k' * gram c P l l' := by have hsq : ∀ p : X × X, (projKernel c M p.1 p.2) ^ 2 = ∑ k, ∑ l, ∑ k', ∑ l', (c p.1 k * M k l * c p.2 l) * (c p.1 k' * M k' l' * c p.2 l') := by intro p unfold projKernel rw [sq, Finset.sum_mul_sum] rw [Finset.sum_congr rfl (fun k _ => Finset.sum_congr rfl (fun k' _ => by rw [Finset.sum_mul_sum]))] rw [Finset.sum_congr rfl (fun k _ => Finset.sum_comm)] have hInt : ∀ k l k' l' : Fin J, Integrable (fun p : X × X => (c p.1 k * M k l * c p.2 l) * (c p.1 k' * M k' l' * c p.2 l')) (P.prod P) := by intro k l k' l' have hX : Integrable (fun x => c x k * c x k') P := (hc k).integrable_mul (hc k') have hY : Integrable (fun y => c y l * c y l') P := (hc l).integrable_mul (hc l') have hprod : Integrable (fun p : X × X => (c p.1 k * c p.1 k') * (c p.2 l * c p.2 l')) (P.prod P) := hX.mul_prod hY have hEq : (fun p : X × X => (c p.1 k * M k l * c p.2 l) * (c p.1 k' * M k' l' * c p.2 l')) = (fun p : X × X => (M k l * M k' l') * ((c p.1 k * c p.1 k') * (c p.2 l * c p.2 l'))) := by funext p ring rw [hEq] exact hprod.const_mul (M k l * M k' l') have hEval : ∀ k l k' l' : Fin J, ∫ p, (c p.1 k * M k l * c p.2 l) * (c p.1 k' * M k' l' * c p.2 l') ∂(P.prod P) = M k l * M k' l' * gram c P k k' * gram c P l l' := by intro k l k' l' have hEq : (fun p : X × X => (c p.1 k * M k l * c p.2 l) * (c p.1 k' * M k' l' * c p.2 l')) = (fun p : X × X => (M k l * M k' l') * ((c p.1 k * c p.1 k') * (c p.2 l * c p.2 l'))) := by funext p ring rw [hEq, integral_const_mul, integral_prod_mul (μ := P) (ν := P) (f := fun x => c x k * c x k') (g := fun y => c y l * c y l')] simp only [gram, Matrix.of_apply] ring simp_rw [hsq] rw [integral_finset_sum] · apply Finset.sum_congr rfl intro k _ rw [integral_finset_sum] · apply Finset.sum_congr rfl intro l _ rw [integral_finset_sum] · apply Finset.sum_congr rfl intro k' _ rw [integral_finset_sum] · apply Finset.sum_congr rfl intro l' _ exact hEval k l k' l' · intro l' _ exact hInt k l k' l' · intro k' _ apply integrable_finset_sum intro l' _ exact hInt k l k' l' · intro l _ apply integrable_finset_sum intro k' _ apply integrable_finset_sum intro l' _ exact hInt k l k' l' · intro k _ apply integrable_finset_sum intro l _ apply integrable_finset_sum intro k' _ apply integrable_finset_sum intro l' _ exact hInt k l k' l'
    Causalean.Stat.Nonparametric.HOIF.projKernel_L2_eq_sum · Causalean/Stat/Nonparametric/HOIF/ProjectedKernelTrace.lean:90
  • sum_collapse_dim theorem — The 4-fold Gram sum collapses to the projection dimension. With the HOIF weighting M = Σ⁻¹ (Σ = gram c P invertible), the expanded L²-energy equals the projection dimension J, because Σ Σ⁻¹ = Σ⁻¹ Σ = 1.
    M S :
    Matrix (Fin J) (Fin J) ℝ
    hu :
    IsUnit S.det
    hM :
    M = S⁻¹
    ∑ k, ∑ l, ∑ k', ∑ l', M k l * M k' l' * S k k' * S l l' = (J : ℝ)
    Proof (Lean source)
    theorem sum_collapse_dim (M S : Matrix (Fin J) (Fin J) ℝ) (hu : IsUnit S.det) (hM : M = S⁻¹) : ∑ k, ∑ l, ∑ k', ∑ l', M k l * M k' l' * S k k' * S l l' = (J : ℝ) := by have hSM : S * M = 1 := by rw [hM]; exact Matrix.mul_nonsing_inv S hu have hMS : M * S = 1 := by rw [hM]; exact Matrix.nonsing_inv_mul S hu -- For fixed k,l, the inner double sum collapses to `M k l * S l k`. have key : ∀ k l : Fin J, (∑ k', ∑ l', M k l * M k' l' * S k k' * S l l') = M k l * S l k := by intro k l rw [Finset.sum_comm] -- ∑ l', ∑ k', M k l * M k' l' * S k k' * S l l' have hinner : ∀ l' : Fin J, (∑ k', M k l * M k' l' * S k k' * S l l') = M k l * S l l' * (S * M) k l' := by intro l' rw [Matrix.mul_apply, Finset.mul_sum] exact Finset.sum_congr rfl (fun k' _ => by ring) rw [Finset.sum_congr rfl (fun l' _ => hinner l'), hSM] simp only [Matrix.one_apply, mul_ite, mul_one, mul_zero] rw [Finset.sum_ite_eq univ k (fun l' => M k l * S l l')] simp rw [Finset.sum_congr rfl (fun k _ => Finset.sum_congr rfl (fun l _ => key k l))] -- ∑ k, ∑ l, M k l * S l k = ∑ k, (M*S) k k = ∑ k, 1 = J have hrow : ∀ k : Fin J, (∑ l, M k l * S l k) = (M * S) k k := fun k => (Matrix.mul_apply).symm rw [Finset.sum_congr rfl (fun k _ => hrow k), hMS] simp only [Matrix.one_apply_eq] rw [Finset.sum_const, Finset.card_univ, Fintype.card_fin, nsmul_eq_mul, mul_one]
    Causalean.Stat.Nonparametric.HOIF.sum_collapse_dim · Causalean/Stat/Nonparametric/HOIF/ProjectedKernelTrace.lean:184
Projection­Risk 1 core · 0 supporting Risk decompositions for localized HOIF estimators, combining first-order variance, projection bias, degenerate U-statistic variance, and higher-order product remainders. ★ hoif_projection_risk_bound

Order-m HOIF projection-risk decomposition (capstone)

Risk decompositions for localized HOIF estimators, combining first-order variance, projection bias, degenerate U-statistic variance, and higher-order product remainders.

The mean-squared error of an order-m HOIF estimator, using a J-dimensional projection space and bandwidth h, splits into three statistically distinct pieces plus the higher-order estimation remainder:

* localized first-order variance V₁ = O((nh)^{-1}) — the AIPW/plug-in stochastic term; * projection product bias² B² = O(J^{-4s/d}) — the squared series/sieve approximation error of the J-term projection (Causalean.Stat.Nonparametric.SeriesSieve); * degenerate U-statistic variance V₂ = Var[Uₙ] ≤ 4C·J/(nh)² — the second-order projected stochastic term, controlled by HOIF.DegenerateUStatVariance from the supplied localized L²-energy hypothesis ζ ≤ C·J/h² (the sibling HOIF.ProjectedKernelTrace proves the inverse-Gram identity ζ = J in the unlocalized case); * order-m product remainder R² ≤ |T|²·δ^{2(m+1)} — the HOIF estimation bias, a finite sum of products of m+1 nuisance -errors (HOIF.ProductRemainder), made o(ρ_n) by choosing m large enough (hoif_order_choice_negligible).

hoif_projection_risk_bound assembles these into a single explicit upper bound on the risk: it takes the bias-variance decomposition as input and discharges the second-order variance term and the product remainder from the Causalean theorems, leaving only V₁ and (supplied by the sibling local-polynomial / series-sieve substrates) as hypotheses.

theorem hoif_projection_risk_bound reviewed
Causalean.Stat.Nonparametric.HOIF

Order-m HOIF projection-risk bound. For an i.i.d. sample S and a projection kernel g, suppose g is symmetric, square-integrable, and doubly degenerate, the sample size n is at least 2, and the bandwidth h is positive, the projection dimension J and trace constant C are nonnegative, and the kernel's L²-energy ζ obeys the trace bound ζ ≤ C·J/h². Suppose further that the first-order variance V1 obeys the rate V1 ≤ Cv1/(nh) and the projection bias² Bsq obeys the rate Bsq ≤ Cb·J^{-4s/d}, and that the order-m estimation remainder R is controlled, over a finite index set T, by a sum of products of m+1 nuisance-error factors: every such factor is nonnegative, every factor is at most the largest nuisance error δ, and the absolute value of R is bounded by that sum of products. If, finally, the estimator's risk decomposes as risk ≤ V1 + Bsq + Var[Uₙ] + R², then the risk is bounded by the explicit sum Cv1/(nh) + Cb·J^{-4s/d} + 4C·J/(nh)² + |T|²·δ^{2(m+1)}.

Formal statement
S :
IIDSample Ω X μ P
hg :
ι :
Type*
T :
e :
ι → ℕ → ℝ
R :
risk V1 Bsq Cv1 Cb C J h s d δ :
n m :
hn :
2 ≤ n
hh :
0 < h
hJ :
0 ≤ J
hC :
0 ≤ C
hzeta :
IIDSample.zeta P g ≤ C * J / h ^ 2
hV1 :
V1 ≤ Cv1 / ((n : ℝ) * h)
hB :
Bsq ≤ Cb * J ^ (-(4 * s / d))
hnn :
∀ t ∈ T, ∀ k ∈ range (m + 1), 0 ≤ e t k
hle :
∀ t ∈ T, ∀ k ∈ range (m + 1), e t k ≤ δ
hRbd :
|R| ≤ ∑ t ∈ T, ∏ k ∈ range (m + 1), e t k
hdecomp :
risk ≤ V1 + Bsq + variance (uStatistic S g n) μ + R ^ 2
risk
≤ Cv1 / ((n : ℝ) * h)
+ Cb * J ^ (-(4 * s / d))
+ 4 * C * J / ((n : ℝ) * h) ^ 2
+ (T.card : ℝ) ^ 2 * δ ^ (2 * (m + 1))
Proof (Lean source)
theorem hoif_projection_risk_bound (S : IIDSample Ω X μ P) (hg : DegenKernel P g) {ι : Type*} (T : Finset ι) (e : ι → ℕ → ℝ) (R : ℝ) {risk V1 Bsq Cv1 Cb C J h s d δ : ℝ} {n m : ℕ} (hn : 2 ≤ n) (hh : 0 < h) (hJ : 0 ≤ J) (hC : 0 ≤ C) (hzeta : IIDSample.zeta P g ≤ C * J / h ^ 2) (hV1 : V1 ≤ Cv1 / ((n : ℝ) * h)) (hB : Bsq ≤ Cb * J ^ (-(4 * s / d))) (hnn : ∀ t ∈ T, ∀ k ∈ range (m + 1), 0 ≤ e t k) (hle : ∀ t ∈ T, ∀ k ∈ range (m + 1), e t k ≤ δ) (hRbd : |R| ≤ ∑ t ∈ T, ∏ k ∈ range (m + 1), e t k) (hdecomp : risk ≤ V1 + Bsq + variance (uStatistic S g n) μ + R ^ 2) : risk ≤ Cv1 / ((n : ℝ) * h) + Cb * J ^ (-(4 * s / d)) + 4 * C * J / ((n : ℝ) * h) ^ 2 + (T.card : ℝ) ^ 2 * δ ^ (2 * (m + 1)) := by have hV2 : variance (uStatistic S g n) μ ≤ 4 * C * J / ((n : ℝ) * h) ^ 2 := degenerate_uStatistic_variance_le S hg hn hh hJ hC hzeta have hRem : R ^ 2 ≤ (T.card : ℝ) ^ 2 * δ ^ (2 * (m + 1)) := hoif_remainder_sq_le T e m δ R hnn hle hRbd calc risk ≤ V1 + Bsq + variance (uStatistic S g n) μ + R ^ 2 := hdecomp _ ≤ Cv1 / ((n : ℝ) * h) + Cb * J ^ (-(4 * s / d)) + 4 * C * J / ((n : ℝ) * h) ^ 2 + (T.card : ℝ) ^ 2 * δ ^ (2 * (m + 1)) := add_le_add (add_le_add (add_le_add hV1 hB) hV2) hRem
Causalean.Stat.Nonparametric.HOIF.hoif_projection_risk_bound · Causalean/Stat/Nonparametric/HOIF/ProjectionRisk.lean:46 · uses DegenKernel , IIDSample , zeta , uStatistic