2 papers
math.NA2026
Preserving Conservation Laws in the Time-Evolving Natural Gradient Method via Relaxation and Projection Techniques
Zihao Shi, Dongling Wang
Neural networks have demonstrated significant potential in solving partial differential equations (PDEs). While global approaches such as Physics-Informed Neural Networks (PINNs) o…
cs.LG2025
Measuring Over-smoothing beyond Dirichlet energy
Weiqi Guan, Zihao Shi
While Dirichlet energy serves as a prevalent metric for quantifying over-smoothing, it is inherently restricted to capturing first-order feature derivatives. To address this limita…