-
Adaptive step sizes for stochastic gradient descent in Hilbert spaces
Article
Optimization Methods and Software, p.1-38 · 2026
doi:10.1080/10556788.2026.2730446
BibLaTeX
@ARTICLE{KoehneKreisSchielaHerzog:2026:1,
AUTHOR = {Köhne, Frederik and Kreis, Leonie and Schiela, Anton and Herzog, Roland},
DATE = {2026-10},
DOI = {10.1080/10556788.2026.2730446},
JOURNALTITLE = {Optimization Methods and Software},
PAGES = {1--38},
TITLE = {Adaptive step sizes for stochastic gradient descent in Hilbert spaces},
}
-
SensLI: sensitivity-based layer insertion for neural networks
Article
Journal of Machine Learning 5(3), p.353-390 · 2026
arXiv:2311.15995
doi:10.4208/jml.251016
BibLaTeX
@ARTICLE{KreisHerbergKoehneSchielaHerzog:2026:1,
AUTHOR = {Kreis, Leonie and Herberg, Evelyn and Köhne, Frederik and Schiela, Anton and Herzog, Roland},
DATE = {2026-07},
DOI = {10.4208/jml.251016},
EPRINT = {2311.15995},
EPRINTTYPE = {arXiv},
JOURNALTITLE = {Journal of Machine Learning},
NUMBER = {3},
PAGES = {353--390},
TITLE = {SensLI: sensitivity-based layer insertion for neural networks},
VOLUME = {5},
}
-
Nonlinear Optimization Techniques Applied to Neural Network Training
Thesis
Ph.D. thesis, Heidelberg University · 2026
doi:10.11588/heidok.00038315
BibLaTeX
@THESIS{Kreis:2026:1,
AUTHOR = {Kreis, Leonie},
INSTITUTION = {Heidelberg University},
DATE = {2026-03-25},
DOI = {10.11588/heidok.00038315},
TITLE = {Nonlinear Optimization Techniques Applied to Neural Network Training},
TYPE = {phdthesis},
}
-
Metric Frobenius norms and inner products of matrices and linear maps
Article
Linear Algebra and its Applications 727, p.112-128 · 2025
arXiv:2311.15419
doi:10.1016/j.laa.2025.08.005
BibLaTeX
@ARTICLE{HerzogKoehneKreisSchiela:2025:1,
AUTHOR = {Herzog, Roland and Köhne, Frederik and Kreis, Leonie and Schiela, Anton},
DATE = {2025-12},
DOI = {10.1016/j.laa.2025.08.005},
EPRINT = {2311.15419},
EPRINTTYPE = {arXiv},
JOURNALTITLE = {Linear Algebra and its Applications},
PAGES = {112--128},
TITLE = {Metric Frobenius norms and inner products of matrices and linear maps},
VOLUME = {727},
}