Risk of the Least Squares Minimum Norm Estimator under the Spike Covariance Model

Mercredi 6 mai 15:30-16:30 - Zacharie Naulet - LMO, Université Paris Saclay

Résumé : We study the risk of the minimum norm linear least squares estimator in when the number of parameters $d$ depends on $n$, and $\fracdn \to \infty$. We assume that data has an underlying low rank structure by restricting ourselves to spike covariance matrices, where a fixed finite number of eigenvalues grow with $n$ and are much larger than the rest of the eigenvalues, which are (asymptotically) in the same order. We show that in this setting the risk of minimum norm least squares estimator vanishes in compare to risk of the null estimator. We give asymptotic and non asymptotic upper bounds for this risk, and also leverage the assumption of spike model to give an analysis of the bias that leads to tighter bounds in comparison with previous works.

Risk of the Least Squares Minimum Norm Estimator under the Spike Covariance Model  Version PDF