Batched and Complete U-Statistics for Trace-Polynomial Estimation from Classical Shadows

arXiv:2608.22962 2026 Regularization 1 ideas extracted · analyzed Aug 29, 2026

What the math gives to ML

The paper's transferable asset is the variance behavior of complete U-statistics versus disjoint batching for polynomial moment estimators. Complete symmetrization Rao–Blackwellizes a batched estimator and suppresses degenerate Hoeffding components from order 1/B to order 1/B^2 for degree-two kernels, which can stabilize high-order moment regularizers. A direct neural-network use is to estimate spectral moments of embedding covariance matrices with all distinct sample pairs rather than pairing examples once, while measuring the computation-versus-gradient-noise tradeoff.

Ideas from this paper

Mechanism works 2026

Complete-U Moment Regularizer

Replace disjoint-pair estimates of embedding covariance moments with a complete U-statistic over every distinct pair in a minibatch. For embeddings z, the degree-two kernel h(z_i,z_j)=(z_i^T z_j)^2 estimates the spectral moment tr(M^2), where M=E[zz^T]; complete symmetrization reduces the degenerate component of estimator variance from O(1/B) to O(1/B^2).

Useful6/10
Difficulty4/10
Novelty5/10
Paper: Batched and Complete U-Statistics for Trace-Polynomial Estimation from Classical Shadows arXiv:2608.22962