Randomized boosting with multivariable base-learners for high-dimensional variable selection and prediction

C Staerk, A Mayr - BMC bioinformatics, 2021 - Springer
Background Statistical boosting is a computational approach to select and estimate
interpretable prediction models for high-dimensional biomedical data, leading to implicit …

Learning from limited temporal data: Dynamically sparse historical functional linear models with applications to Earth science

J Janssen, S Meng, A Haris, S Schrunner, J Cao… - arXiv preprint arXiv …, 2023 - arxiv.org
Scientists and statisticians often want to learn about the complex relationships that connect
two variables that vary over time. Recent work on sparse functional historical linear models …

High-dimensional variable selection via low-dimensional adaptive learning

C Staerk, M Kateri, I Ntzoufras - 2021 - projecteuclid.org
A stochastic search method, the so-called Adaptive Subspace (AdaSub) method, is
proposed for variable selection in high-dimensional linear regression models. The method …

A Metropolized adaptive subspace algorithm for high-dimensional Bayesian variable selection

C Staerk, M Kateri, I Ntzoufras - Bayesian Analysis, 2024 - projecteuclid.org
A Metropolized Adaptive Subspace Algorithm for High-Dimensional Bayesian Variable Selection
Page 1 Bayesian Analysis (2024) 19, Number 1, pp. 261–291 A Metropolized Adaptive …

High-dimensional variable selection via low-dimensional adaptive learning

C Staerk, M Kateri, I Ntzoufras - Ulmer Informatik-Berichte, 2017 - spotseven.de
Nowadays one often faces the challenging scenario in which high-dimensional data is
observed. In a high-dimensional setting, where the number of explanatory variables p is …

Boosting with random selection of weak learners for variable selection in high-dimensional models

C Staerk, A Mayr - Ulmer Informatik-Berichte, 2019 - d-nb.info
Statistical boosting is a promising alternative to popular regularization methods such as the
Lasso [1] for fitting high-dimensional models with many possible explanatory variables: early …