The computation is a weighted-$L^2$ projection whose core normal-system correspondence is machine-checked in Lean 4.5, and gives the exact finite-order excess $L^2(P)$ risk of this mismatch.
Abstract
Wiener-Hermite cross-correlation identification represents a polynomial response in the Hermite basis. Under Gaussian excitation the basis is orthogonal and a diagonal rule recovers it exactly; under non-Gaussian excitation the same basis is kept, but its Gram matrix gains off-diagonal terms and the diagonal rule is no longer the population projection. We give the exact finite-order excess $L^2(P)$ risk of this mismatch: a moment quadratic form from two Hankel-Cholesky factorizations and one diagonal solve, at $O(s^3)$ cost from moments to order $2s$. Closed cumulant forms at orders three and four expose which non-Gaussian features drive it; symmetry protects the Gaussian basis only through order two. A bootstrap decides, from data, whether a matched basis is worth building; on a Wiener-Hammerstein benchmark it separates a near-Gaussian channel (penalty $\approx 10^{-4}$) from a skewed output (penalty $0.05$). The computation is a weighted-$L^2$ projection whose core normal-system correspondence is machine-checked in Lean 4.
Higher-order cumulants capture the non-Gaussian dependence that covariance misses, but they are hard to use in high dimensions. An order-$d$ cumulant tensor has $p^d$ entries, and the plug-in sample cumulant is generally not even rate-optimal under the tensor spectral norm. For ordered data, both difficulties admit one remedy: assuming that higher-order interactions decay away from the main tensor diagonal, we introduce a bandable cumulant class and a tapered sample cumulant estimator that computes only $O(pk^{d-1})$ local entries at bandwidth $k$ and never forms the full tensor. Under exponential-type tail conditions, we prove nonasymptotic spectral-norm bounds that separate tapering bias from stochastic error, and a minimax lower bound over the same class that matches the leading bias and stochastic terms of the upper bound; for sub-Gaussian observations, the tapered estimator attains the minimax rate whenever $n\gg(k+\log p)^{d-1}$ at the oracle bandwidth $k$, with the ambient dimension entering only through $\log p$. Localization also suppresses the higher-order fluctuations behind this suboptimality, so tapering plays a stronger role here than in bandable covariance estimation. The spectral-norm guarantee transfers directly to downstream tasks, yielding plug-in error bounds for cumulant Yule--Walker estimation in autoregressive models, minimum-distance estimation in moving-average models, and matched-filter source localization in sensor arrays. Simulations corroborate the theory, and real-data analyses of RR-interval, air-quality, and Neuropixels recordings illustrate the resulting stability gains.
Runshi Tang, An-Ru R. Zhang, Yuefeng Han et al.· 0 citations
A dimension-free version of the retained-energy form of the Mallat--Zeitouni conjecture is established, showing that the KL basis is within this factor of the optimal basis, and shows that the possible advantage of optimizing over all orthonormal bases vanishes as $d$ grows.
Minbo Gao, Zheng-Feng Ji, Cheng-Hua Liu· 0 citations
For two Gaussian random elements on a separable Hilbert space with common covariance operator, the fourth-order moment tensor structure of their mixture admits an operator-valued representation obtained from the purely quadratic component of the class-conditional second moment. We identify the tensor mechanism generating the completely diagonal coefficients of this fourth-order representation after covariance standardization, and show that these coefficients are governed entirely by the coordinatewise Cameron-Martin energy of the mean shift. This yields a necessary and sufficient condition, together with an explicit eigenvalue, for the Fisher discriminant to be an eigenfunction of the induced coordinatewise operator. We further introduce aggregated fourth-order spectral functionals for two complementary constructions, one built from fourth-order moments and the other from a product-of-expectations counterpart, and prove that they are asymptotically equivalent precisely when the underlying Gaussian measures are mutually singular. These results provide a spectral realization of the classical Cameron-Martin criterion through higher-order moment operators, explaining the probabilistic origin of fourth-order spectral quantities previously proposed for Gaussian discrimination and functional data classification and relating them to the"near-perfect classification"regime.
Exhaustive moment fitting in this constant-dimensional space produces a proper mixture and, together with the dimension-free moment characterization of Gaussian mixtures, achieves the optimal Hellinger rate in polynomial arithmetic time for every fixed $k$.
We characterize the weak closure of uniformly $L^2$-bounded vectors in a fixed Wiener chaos when the underlying Gaussian Hilbert spaces may vary. On a represented subsequence, each physical-weight tensor space splits into a decomposable closed span and its primitive orthogonal complement. Primitive-block evaluation extends to a unitary weighted Fock representation. Hence the weak limits of a $q$th chaos are exactly the weighted Wiener polynomials indexed by partitions of $q$, and every such terminal is realized by homogeneous $q$-fold Wiener integrals. Each represented terminal has a minimal separable graded support, unique up to graded orthogonal transformations. We construct a positive Hilbert-Stein extraction. After $J$ steps, its residual Gaussian and interface defects are $O(J^{-1})$, while the Stein factorization error is $O(J^{-1/2})$. The remaining active and covariance comparisons have no bounded-energy rate. In homogeneous chaos, Gram-reduced feedback converges to the decomposable and primitive Fock projections; the latter is the canonical independent Gaussian factor. The vanishing of all marginal fourth cumulants is equivalent to disappearance of the decomposable projection, recovering the vector fourth-moment theorem with a characteristic-function bound. For finite mixed degrees, a weightwise triangular procedure removes the ghost obstruction and recovers the maximal Gaussian factor detected by all one-leg contractions.
This work defines empirical plug-in estimators and prove distribution-free uniform convergence under finite-moment assumptions, before detailing three practical solvers: a Picard-style orthogonal optimizer for ICA, an exhaustive dynamic program for causal order search, and a greedy order search variant.
F'elix Laplante, C. Ambroise, Pierre Humbert· 1 citation
