7 papers
Higher-order spectral perturbation expansions II: Kernel matrices and manifold learning
Bernhard Stankewitz, Martin Wahl
We study spectral concentration bounds for kernel matrices as approximation of the corresponding kernel integral operator. Results are established under weak assumptions on the dat…
Provable Mixed-Noise Learning with Flow-Matching
Paul Hagemann, Robert Gruhlke, Bernhard Stankewitz +2
We study Bayesian inverse problems with mixed noise, modeled as a combination of additive and multiplicative Gaussian components. While traditional inference methods often assume f…
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…
Contraction rates for conjugate gradient and Lanczos approximate posteriors in Gaussian process regression
Bernhard Stankewitz, Botond Szabo
Due to their flexibility and theoretical tractability Gaussian process (GP) regression models have become a central topic in modern statistics and machine learning. While the true…
Early stopping for -boosting in high-dimensional linear models
Bernhard Stankewitz
Increasingly high-dimensional data sets require that estimation methods do not only satisfy statistical guarantees but also remain computationally feasible. In this context, we con…
From inexact optimization to learning via gradient concentration
Bernhard Stankewitz, Nicole Mücke, Lorenzo Rosasco
Optimization in machine learning typically deals with the minimization of empirical objectives defined by training data. However, the ultimate goal of learning is to minimize the e…
Smoothed residual stopping for statistical inverse problems via truncated SVD estimation
Bernhard Stankewitz
This work examines under what circumstances adaptivity for truncated SVD estimation can be achieved by an early stopping rule based on the smoothed residuals $ \| ( A A^{\top} )^{α…