Steffen Schotthöfer

24 papers A* 4Journal 20

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Compressing Vision Transformers in Geospatial Transfer Learning with Manifold-Constrained Optimization. CoRR Thomas Snyder, H. Lexie Yang, Stefan Schnake, Steffen Schotthöfer
2026	J	`jnl`	Tucker Attention: A generalization of approximate attention mechanisms. CoRR Timon Klein, Jonas Kusch, Sebastian Sager, Stefan Schnake, Steffen Schotthöfer
2025	J	`jnl`	A geometric framework for momentum-based optimizers for low-rank training. CoRR Steffen Schotthöfer, Timon Klein, Jonas Kusch
2025	J	`jnl`	An Augmented Backward-Corrected Projector Splitting Integrator for Dynamical Low-Rank Training. CoRR Jonas Kusch, Steffen Schotthöfer, Alexandra Walter
2025	J	`jnl`	Data-Driven Filtering of the Spherical Harmonics Method. CoRR Benjamin Plumridge, Cory D. Hauck, Steffen Schotthöfer
2025	J	`jnl`	Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks. CoRR Steffen Schotthöfer, H. Lexie Yang, Stefan Schnake
2025	A*	`conf`	GeoLoRA: Geometric integration for parameter efficient fine-tuning. ICLR Steffen Schotthöfer, Emanuele Zangrando, Gianluca Ceruti, Francesco Tudisco, Jonas Kusch
2025	J	`jnl`	Structure-preserving neural networks for the regularized entropy-based closure of a linear, kinetic, radiative transport equation. J. Comput. Phys. Steffen Schotthöfer, M. Paul Laiu, Martin Frank, Cory D. Hauck
2024	J	`jnl`	Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees. CoRR Steffen Schotthöfer, M. Paul Laiu
2024	J	`jnl`	GeoLoRA: Geometric integration for parameter efficient fine-tuning. CoRR Steffen Schotthöfer, Emanuele Zangrando, Gianluca Ceruti, Francesco Tudisco, Jonas Kusch
2024	A*	`conf`	Geometry-aware training of factorized layers in tensor Tucker format. NeurIPS Emanuele Zangrando, Steffen Schotthöfer, Gianluca Ceruti, Jonas Kusch, Francesco Tudisco
2024	J	`jnl`	Structure-Preserving Operator Learning: Modeling the Collision Operator of Kinetic Equations. CoRR Jae Yong Lee, Steffen Schotthöfer, Tianbai Xiao, Sebastian Krumscheid, Martin Frank
2024	J	`jnl`	Structure-preserving neural networks for the regularized entropy-based closure of the Boltzmann moment system. CoRR Steffen Schotthöfer, M. Paul Laiu, Martin Frank, Cory D. Hauck
2024	J	`jnl`	Windowing Regularization Techniques for Unsteady Aerodynamic Shape Optimization. CoRR Steffen Schotthöfer, Beckett Y. Zhou, Tim Albring, Nicolas R. Gauger
2023	J	`jnl`	Conservation properties of the augmented basis update & Galerkin integrator for kinetic problems. CoRR Lukas Einkemmer, Jonas Kusch, Steffen Schotthöfer
2023	J	`jnl`	KiT-RT: An Extendable Framework for Radiative Transfer and Therapy. ACM Trans. Math. Softw. Jonas Kusch, Steffen Schotthöfer, Pia Stammer, Jannick Wolters, Tianbai Xiao
2023	J	`jnl`	Predicting continuum breakdown with deep neural networks. J. Comput. Phys. Tianbai Xiao, Steffen Schotthöfer, Martin Frank
2023	J	`jnl`	Rank-adaptive spectral pruning of convolutional layers during training. CoRR Emanuele Zangrando, Steffen Schotthöfer, Gianluca Ceruti, Jonas Kusch, Francesco Tudisco
2022	J	`jnl`	KiT-RT: An extendable framework for radiative transfer and therapy. CoRR Jonas Kusch, Steffen Schotthöfer, Pia Stammer, Jannick Wolters, Tianbai Xiao
2022	A*	`conf`	Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations. NeurIPS Steffen Schotthöfer, Emanuele Zangrando, Jonas Kusch, Gianluca Ceruti, Francesco Tudisco
2022	J	`jnl`	Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations. CoRR Steffen Schotthöfer, Emanuele Zangrando, Jonas Kusch, Gianluca Ceruti, Francesco Tudisco
2022	J	`jnl`	Neural network-based, structure-preserving entropy closures for the Boltzmann moment system. CoRR Steffen Schotthöfer, Tianbai Xiao, Martin Frank, Cory D. Hauck
2022	A*	`conf`	Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann Equation. ICML Steffen Schotthöfer, Tianbai Xiao, Martin Frank, Cory D. Hauck
2021	J	`jnl`	A structure-preserving surrogate model for the closure of the moment system of the Boltzmann equation using convex deep neural networks. CoRR Steffen Schotthöfer, Tianbai Xiao, Martin Frank, Cory D. Hauck