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

Documenti analoghi

• Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
  di: Schotthöfer, Steffen, et al.
  Pubblicazione: (2025)
• Geometry-aware training of factorized layers in tensor Tucker format
  di: Zangrando, Emanuele, et al.
  Pubblicazione: (2023)
• GeoLoRA: Geometric integration for parameter efficient fine-tuning
  di: Schotthöfer, Steffen, et al.
  Pubblicazione: (2024)
• Construction of high-order conservative basis-update and Galerkin dynamical low-rank integrators
  di: Einkemmer, Lukas, et al.
  Pubblicazione: (2023)
• Structure-preserving neural networks for the regularized entropy-based closure of the Boltzmann moment system
  di: Schotthöfer, Steffen, et al.
  Pubblicazione: (2024)