3 papers
cs.LG2026
Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks
Jing Xiao, Xinhai Chen, Qinglin Wang +5
Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients.…
cs.LG2026
Prior-Guided Symbolic Regression: Towards Scientific Consistency in Equation Discovery
Jing Xiao, Xinhai Chen, Jiaming Peng +7
Symbolic Regression (SR) aims to discover interpretable equations from observational data, with the potential to reveal underlying principles behind natural phenomena. However, exi…
cs.LG2025
MeshONet: A Generalizable and Efficient Operator Learning Method for Structured Mesh Generation
Jing Xiao, Xinhai Chen, Qingling Wang +1
Mesh generation plays a crucial role in scientific computing. Traditional mesh generation methods, such as TFI and PDE-based methods, often struggle to achieve a balance between ef…