Humboldt-Universität zu Berlin - Mathematisch-Naturwissenschaftliche Fakultät - Institut für Mathematik

Patrick Rebeschini

Implicit regularization in statistical learning: An overview

Coffee Break

Bernhard Stankewitz

Early stopping for $L^{2}$-boosting in sparse high-dimensional linear models

Alain Celisse

Early stopping and regularization by projection for spectral filter estimators

Garvesh Raskutti

Early stopping and regularization: From kernel methods to variable importance in neural networks

Coffee Break

Sylvain Arlot

Cross-validation for estimator selection

Perspectives

Workshop Dinner 

Laura Hucker and Markus Reiß

Early stopping for conjugate gradients in statistical inverse problems

Tim Jahn

Early stopping of untrained convolutional networks

Nicole Mücke

Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problem

Lunch