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.
PAC-Bayesian bounds for the Gram matrix and least squares regression with a random design
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The topics dicussed in this paper take their origin inthe estimation of the Gram matrix of a random vector from a sample made of n independent copies. They comprise the estimation of the covariance matrix and the study of least squares regression with a random design. We propose four types of results, based on non-asymptotic PAC-Bayesian generalization bounds: a new robust estimator of the Gram matrix and of the covariance matrix, new results on the empirical Gram matrix, new robust least squares estimators and new results on the ordinary least squares estimator, including its exact rate of convergence under polynomial moment assumptions.
fields
math.ST 1years
2026 1verdicts
ACCEPT 1representative citing papers
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.