activity
20182021
most citedOn the perturbation series for eigenvalues and eigenprojections

2 citations · 2 across the 4 of their papers we have counts for

collaborators

7 papers

math.ST2021

Functional estimation in log-concave location families

Vladimir Koltchinskii, Martin Wahl

Let be a log-concave location family with where is a known convex function and let $X_1,\…

math.ST2021

Van Trees inequality, group equivariance, and estimation of principal subspaces

Martin Wahl

We establish non-asymptotic lower bounds for the estimation of principal subspaces. As applications, we obtain new results for the excess risk of principal component analysis and t…

math.ST2020

Analyzing the discrepancy principle for kernelized spectral filter learning algorithms

Alain Celisse, Martin Wahl

We investigate the construction of early stopping rules in the nonparametric regression problem where iterative learning algorithms are used and the optimal iteration number is unk…

math.FA20192 cited

On the perturbation series for eigenvalues and eigenprojections

Martin Wahl

A standard perturbation result states that perturbed eigenvalues and eigenprojections admit a perturbation series provided that the operator norm of the perturbation is smaller tha…

math.ST2019

High-probability bounds for the reconstruction error of PCA

Cassandra Milbradt, Martin Wahl

We derive high-probability bounds for the reconstruction error of PCA in infinite dimensions. We apply our bounds in the case that the eigenvalues of the covariance operator satisf…

math.ST2018

A note on the prediction error of principal component regression

Martin Wahl

We analyse the prediction error of principal component regression (PCR) and prove non-asymptotic upper bounds for the corresponding squared risk. Under mild assumptions, we show th…