University of Münster
CRIS@UM
DE | EN

Dr. Benno Kuckuck

Current affiliations

Publications

An overview on deep learning-based approximation methods for partial differential equations
Beck C, Hutzenthaler M, Jentzen A, Kuckuck B (2023)
In: Discrete and Continuous Dynamical Systems - Series B, 28(6), 3697-3746. doi:10.3934/dcdsb.2022238
Research article (journal) | Peer reviewed | Published
Deep learning approximations for non-local nonlinear PDEs with Neumann boundary conditions
Boussange, V.; Becker, S.; Jentzen, A.; Kuckuck, B.; Pellissier, L. (2023)
In: SN Partial Differential Equations and Applications, 4, 51. doi:10.1007/s42985-023-00244-0
Research article (journal) | Peer reviewed | Published
Counterexamples to local Lipschitz and local Hölder continuity with respect to the initial values for additive noise driven SDEs with smooth drift coefficient functions with at most polynomially growing derivatives
Jentzen A, Kuckuck B, Müller-Gronbach T, Yaroslavtseva L (2022)
In: Discrete and Continuous Dynamical Systems - Series B, 27(7), 3707-3724. doi:10.3934/dcdsb.2021203
Research article (journal) | Peer reviewed | Published
Full error analysis for the training of deep neural networks
Beck C, Jentzen A, Kuckuck B (2022)
In: Infinite Dimensional Analysis, Quantum Probability and Related Topics, 25(2), 2150020. doi:10.1142/S021902572150020X
Research article (journal) | Peer reviewed | Published
Strong error analysis for stochastic gradient descent optimization algorithms
Jentzen A, Kuckuck B, Neufeld A, von Wurstemberger P (2021)
In: IMA Journal of Numerical Analysis, 41(1), 455-492. doi:10.1093/imanum/drz055
Research article (journal) | Peer reviewed | Published
Show all publications (14)

Projects

EXC 2044 - T10: Deep learning and surrogate methods
Duration: 01/01/2026 - 31/12/2032 | 1st Funding period
Funded by: DFG - Cluster of Excellence
Type of project: Subproject in DFG-joint project hosted at University of Münster
Mathematical Theory for Deep Learning (DLMATH)
Duration: 01/09/2019 - 31/08/2024
Type of project: Own resources project