Personal information

Websites & social links

Google Scholar
LinkedIn

Activities

Collapse all

Works (17)

An Augmented Backward-Corrected Projector Splitting Integrator for Dynamical Low-Rank Training

2025 | Other
URI:

https://arxiv.org/abs/2502.03006
Contributors: Jonas Kusch; Steffen Schotthöfer; Alexandra Walter
Source: Self-asserted source
Steffen Schotthöfer

Structure-preserving neural networks for the regularized entropy-based closure of a linear, kinetic, radiative transport equation

Journal of Computational Physics
2025-03 | Journal article
DOI: 10.1016/j.jcp.2025.113967
Contributors: Steffen Schotthöfer; M. Paul Laiu; Martin Frank; Cory D. Hauck
Source: check_circle
Crossref

Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees

2024 | Other
URI:

https://arxiv.org/abs/2406.17887
Contributors: Steffen Schotthöfer; M. Paul Laiu
Source: Self-asserted source
Steffen Schotthöfer

GeoLoRA: Geometric integration for parameter efficient fine-tuning

2024 | Other
URI:

https://arxiv.org/abs/2410.18720
Contributors: Steffen Schotthöfer; Emanuele Zangrando; Gianluca Ceruti; Francesco Tudisco; Jonas Kusch
Source: Self-asserted source
Steffen Schotthöfer

Geometry-aware training of factorized layers in tensor Tucker format

Advances in Neural Information Processing Systems
2024 | Conference paper
URI:

https://proceedings.neurips.cc/paper_files/paper/2024/file/ea48cb23a02ec3b895b0b0124307b0ec-Paper-Conference.pdf
Contributors: Zangrando, Emanuele; Schotthöfer, Steffen; Ceruti, Gianluca; Kusch, Jonas; Tudisco, Francesco; A. Globerson; L. Mackey; D. Belgrave; A. Fan; U. Paquet et al.
Source: Self-asserted source
Steffen Schotthöfer

Structure-preserving neural networks for the regularized entropy-based closure of the Boltzmann moment system

2024 | Other
Contributors: Steffen Schotthöfer; M. Paul Laiu; Martin Frank; Cory D. Hauck
Source: Self-asserted source
Steffen Schotthöfer

Structure-Preserving Operator Learning: Modeling the Collision Operator of Kinetic Equations

2024 | Other
Contributors: Jae Yong Lee; Steffen Schotthöfer; Tianbai Xiao; Sebastian Krumscheid; Martin Frank
Source: Self-asserted source
Steffen Schotthöfer

Conservation properties of the augmented basis update & Galerkin integrator for kinetic problems

2023 | Other
Contributors: Lukas Einkemmer; Jonas Kusch; Steffen Schotthöfer
Source: Self-asserted source
Steffen Schotthöfer

Rank-adaptive spectral pruning of convolutional layers during training

2023 | Other
Contributors: Emanuele Zangrando; Steffen Schotthöfer; Gianluca Ceruti; Jonas Kusch; Francesco Tudisco
Source: Self-asserted source
Steffen Schotthöfer

KiT-RT: An Extendable Framework for Radiative Transfer and Therapy

ACM Transactions on Mathematical Software
2023-12-31 | Journal article
DOI: 10.1145/3630001
Contributors: Jonas Kusch; Steffen Schotthöfer; Pia Stammer; Jannick Wolters; Tianbai Xiao
Source: check_circle
Crossref

Predicting continuum breakdown with deep neural networks

Journal of Computational Physics
2023-09 | Journal article
DOI: 10.1016/j.jcp.2023.112278
Part of ISSN: 0021-9991
Contributors: Tianbai Xiao; Steffen Schotthöfer; Martin Frank
Source: Self-asserted source
Steffen Schotthöfer

Synergies between Numerical Methods for Kinetic Equations and Neural Networks

2023-06-05 | Supervised student publication | Author
DOI: 10.5445/IR/1000158838
Contributors: Steffen Schotthöfer; Martin Frank; André Platzer; Cory D. Hauck
Source: check_circle
Repository KITopen (Karlsruhe Institute of Technology)

Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations

Advances in Neural Information Processing Systems
2022 | Conference paper
URI:

https://proceedings.neurips.cc/paper_files/paper/2022/file/7e98b00eeafcdaeb0c5661fb9355be3a-Paper-Conference.pdf
Contributors: Schotthöfer, Steffen; Zangrando, Emanuele; Kusch, Jonas; Ceruti, Gianluca; Tudisco, Francesco; S. Koyejo; S. Mohamed; A. Agarwal; D. Belgrave; K. Cho et al.
Source: Self-asserted source
Steffen Schotthöfer

Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann Equation

Proceedings of the 39th International Conference on Machine Learning
2022 | Conference paper
URI:

https://proceedings.mlr.press/v162/schotthofer22a.html
Contributors: Schotthöfer, Steffen; Xiao, Tianbai; Frank, Martin; Hauck, Cory; Chaudhuri, Kamalika; Jegelka, Stefanie; Song, Le; Szepesvari, Csaba; Niu, Gang; Sabato, Sivan
Source: Self-asserted source
Steffen Schotthöfer

A structure-preserving surrogate model for the closure of the moment system of the Boltzmann equation using convex deep neural networks

2021-07-28 | Conference paper | Author
DOI: 10.2514/6.2021-2895
Contributors: Steffen Schotthöfer; Tianbai Xiao; Martin Frank; Cory Hauck
Source: check_circle
Repository KITopen (Karlsruhe Institute of Technology)

Windowing Regularization Techniques for Unsteady Aerodynamic Shape Optimization

2020-06-08 | Conference paper | Author
DOI: 10.2514/6.2020-3130
Contributors: Steffen Schotthöfer; Beckett Yx Zhou; Tim A. Albring; Nicolas R. Gauger
Source: check_circle
Repository KITopen (Karlsruhe Institute of Technology)

A Numerical Comparison of Consensus-Based Global Optimization to other Particle-based Global Optimization Schemes

PAMM
2018 | Journal article
DOI: https://doi.org/10.1002/pamm.201800291
Contributors: Totzeck, Claudia; Pinnau, René; Blauth, Sebastian; Schotthöfer, Steffen
Source: Self-asserted source
Steffen Schotthöfer

Peer review (2 reviews for 1 publication/grant)

Review activity for Journal of computational physics. (2)
How many people are using ORCID?