3 papers
stat.ML2026
Comparing regularisation paths of (conjugate) gradient estimators in ridge regression
Laura Hucker, Markus ReiÃ, Thomas Stark
We consider standard gradient descent, gradient flow and conjugate gradients as iterative algorithms for minimising a penalised ridge criterion in linear regression. While it is we…
stat.ML2025
EarlyStopping: Implicit Regularization for Iterative Learning Procedures in Python
Eric Ziebell, Ratmir Miftachov, Bernhard Stankewitz +1
Iterative learning procedures are ubiquitous in machine learning and modern statistics. Regularision is typically required to prevent inflating the expected loss of a procedure in…
math.ST2024
Early stopping for conjugate gradients in statistical inverse problems
Laura Hucker, Markus ReiÃ
We consider estimators obtained by iterates of the conjugate gradient (CG) algorithm applied to the normal equation of prototypical statistical inverse problems. Stopping the CG al…