The minimax rate for estimating d-th order moment tensors is sqrt(p/n) wedge 1, while low-degree evidence shows detection of vanishing cumulants is hard for n much less than p to the d/2, creating a reverse detection-estimation gap.
Revisit cp tensor decomposition: Statistical optimality and fast convergence.arXiv preprint arXiv:2505.23046, 2025a
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Proposes scaling-based spectral estimators for discrete multiview density tensors under heteroskedastic multinomial sampling, with Frobenius and l1 bounds and minimax results showing fiber-mass dependence is unavoidable.
A three-phase alternating-update method for asymmetric tensor PCA achieves d to the power of k-minus-2 sample complexity with d-squared memory and improves when signal vectors align.
A functional tensor model with common invariant subspaces and RKHS estimation for analyzing dynamic multilayer networks, applied to bike-share and food-trade data.
citing papers explorer
-
Detection Is Harder Than Estimation in Certain Regimes: Inference for Moment and Cumulant Tensors
The minimax rate for estimating d-th order moment tensors is sqrt(p/n) wedge 1, while low-degree evidence shows detection of vanishing cumulants is hard for n much less than p to the d/2, creating a reverse detection-estimation gap.
-
Optimal Estimation of Discrete Multiview Distributions under Heteroskedastic Multinomial Sampling
Proposes scaling-based spectral estimators for discrete multiview density tensors under heteroskedastic multinomial sampling, with Frobenius and l1 bounds and minimax results showing fiber-mass dependence is unavoidable.
-
Mild Over-Parameterization Benefits Asymmetric Tensor PCA
A three-phase alternating-update method for asymmetric tensor PCA achieves d to the power of k-minus-2 sample complexity with d-squared memory and improves when signal vectors align.
-
A functional tensor model for dynamic multilayer networks with common invariant subspaces and the RKHS estimation
A functional tensor model with common invariant subspaces and RKHS estimation for analyzing dynamic multilayer networks, applied to bike-share and food-trade data.