A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks

Documenti analoghi

• Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers
  di: Zhang, Enrui, et al.
  Pubblicazione: (2022)
• Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers
  di: Chen, Chuqi, et al.
  Pubblicazione: (2024)
• Error Analysis and Numerical Algorithm for PDE Approximation with Hidden-Layer Concatenated Physics Informed Neural Networks
  di: Qian, Yianxia, et al.
  Pubblicazione: (2024)
• U-HNO: A U-shaped Hybrid Neural Operator with Sparse-Point Adaptive Routing for Non-stationary PDE Dynamics
  di: Ma, Yingzhe, et al.
  Pubblicazione: (2026)
• Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
  di: Wang, Hong, et al.
  Pubblicazione: (2025)